feat(imap): handle UIDVALIDITY changes via Message-ID comparison instead of full rebuild

crates/core/src/imap/client.rs

@@ -34,6 +34,25 @@ use std::ops::DerefMut;
 use tokio::io::BufWriter;
 use tracing::debug;
 
+/// Classify an `io::Error` (from TLS stream I/O) for IMAP connection errors.
+/// `UnexpectedEof` is treated as a network error because many servers skip
+/// the TLS `close_notify` alert, causing rustls to emit this error when the
+/// TCP connection is dropped normally.
+fn classify_io_error(e: &std::io::Error) -> ErrorCode {
+    use std::io::ErrorKind;
+    matches!(
+        e.kind(),
+        ErrorKind::BrokenPipe
+            | ErrorKind::ConnectionReset
+            | ErrorKind::ConnectionAborted
+            | ErrorKind::TimedOut
+            | ErrorKind::UnexpectedEof
+            | ErrorKind::NotConnected
+    )
+    .then_some(ErrorCode::NetworkError)
+    .unwrap_or(ErrorCode::ImapCommandFailed)
+}
+
 #[derive(Debug)]
 pub(crate) struct Client {
     inner: ImapClient<Box<dyn SessionStream>>,
@@ -141,7 +160,7 @@ impl Client {
         let _greeting = client
             .read_response()
             .await
-            .map_err(|e| raise_error!(format!("{:#?}", e), ErrorCode::ImapCommandFailed))?
+            .map_err(|e| raise_error!(format!("{:#?}", e), classify_io_error(&e)))?
             .ok_or_else(|| {
                 raise_error!(
                     "Failed to read IMAP greeting — this usually indicates an incorrect encryption setting (SSL vs. STARTTLS). Your current setting is SSL.".into(),
@@ -171,7 +190,7 @@ impl Client {
         let _greeting = client
             .read_response()
             .await
-            .map_err(|e| raise_error!(format!("{:#?}", e), ErrorCode::ImapCommandFailed))?
+            .map_err(|e| raise_error!(format!("{:#?}", e), classify_io_error(&e)))?
             .ok_or_else(|| {
                 raise_error!(
                     "failed to read greeting".into(),
@@ -202,7 +221,7 @@ impl Client {
         let _greeting = client
             .read_response()
             .await
-            .map_err(|e| raise_error!(format!("{:#?}", e), ErrorCode::ImapCommandFailed))?
+            .map_err(|e| raise_error!(format!("{:#?}", e), classify_io_error(&e)))?
             .ok_or_else(|| {
                 raise_error!(
                     "Failed to read IMAP greeting — this usually indicates an incorrect encryption setting (SSL vs. STARTTLS). Your current setting is STARTTLS.".into(),

crates/core/src/imap/executor.rs

@@ -27,7 +27,7 @@ use crate::{error::BichonResult, imap::manager::ImapConnectionManager};
 use async_imap::types::Name;
 use async_imap::Session;
 use futures::TryStreamExt;
-use std::collections::HashSet;
+use std::collections::{HashMap, HashSet};
 use tokio_util::sync::CancellationToken;
 use tracing::info;
 
@@ -260,7 +260,9 @@ impl ImapExecutor {
         let mut count = 0u64;
         let mut skipped = 0u64;
         let mut max_uid: Option<u32> = None;
-        let size_limit = account.max_email_size_bytes.unwrap_or(DEFAULT_MAX_EMAIL_SIZE);
+        let size_limit = account
+            .max_email_size_bytes
+            .unwrap_or(DEFAULT_MAX_EMAIL_SIZE);
         while let Some(fetch) = stream
             .try_next()
             .await
@@ -363,14 +365,14 @@ impl ImapExecutor {
             let mut size_stream = session
                 .fetch(sequence_set.as_str(), SIZE_ONLY_FETCH)
                 .await
-                .map_err(|e| {
-                    raise_error!(format!("{:#?}", e), classify_imap_error(&e))
-                })?;
+                .map_err(|e| raise_error!(format!("{:#?}", e), classify_imap_error(&e)))?;
 
             let mut uids: Vec<u32> = Vec::new();
-            while let Some(fetch) = size_stream.try_next().await.map_err(|e| {
-                raise_error!(format!("{:#?}", e), classify_imap_error(&e))
-            })? {
+            while let Some(fetch) = size_stream
+                .try_next()
+                .await
+                .map_err(|e| raise_error!(format!("{:#?}", e), classify_imap_error(&e)))?
+            {
                 let uid = fetch.uid.unwrap_or(0);
                 let msg_size = fetch.size.unwrap_or(0) as u64;
                 if msg_size == 0 || msg_size <= limit {
@@ -437,14 +439,14 @@ impl ImapExecutor {
             let mut size_stream = session
                 .uid_fetch(uid_set, SIZE_ONLY_FETCH)
                 .await
-                .map_err(|e| {
-                    raise_error!(format!("{:#?}", e), classify_imap_error(&e))
-                })?;
+                .map_err(|e| raise_error!(format!("{:#?}", e), classify_imap_error(&e)))?;
 
             let mut uids: Vec<u32> = Vec::new();
-            while let Some(fetch) = size_stream.try_next().await.map_err(|e| {
-                raise_error!(format!("{:#?}", e), classify_imap_error(&e))
-            })? {
+            while let Some(fetch) = size_stream
+                .try_next()
+                .await
+                .map_err(|e| raise_error!(format!("{:#?}", e), classify_imap_error(&e)))?
+            {
                 let uid = fetch.uid.unwrap_or(0);
                 let msg_size = fetch.size.unwrap_or(0) as u64;
                 if msg_size == 0 || msg_size <= limit {
@@ -550,6 +552,37 @@ impl ImapExecutor {
     ) -> BichonResult<Session<Box<dyn SessionStream>>> {
         ImapConnectionManager::build(account_id).await
     }
+
+    /// Fetch UID → Message-ID mapping without downloading bodies.
+    /// `uid_set` is an IMAP sequence-set string (e.g. "1:100" or "1,3,5").
+    pub async fn fetch_uid_metadata(
+        session: &mut Session<Box<dyn SessionStream>>,
+        uid_set: &str,
+        token: CancellationToken,
+    ) -> BichonResult<HashMap<u32, Option<String>>> {
+        let mut stream = session
+            .uid_fetch(uid_set, "(UID BODY.PEEK[HEADER])")
+            .await
+            .map_err(|e| raise_error!(format!("{:#?}", e), classify_imap_error(&e)))?;
+
+        let mut result = HashMap::new();
+        while let Some(fetch) = stream
+            .try_next()
+            .await
+            .map_err(|e| raise_error!(format!("{:#?}", e), classify_imap_error(&e)))?
+        {
+            if token.is_cancelled() {
+                return Err(raise_error!(
+                    "Stream cancelled".into(),
+                    ErrorCode::InternalError
+                ));
+            }
+            let uid = fetch.uid.unwrap_or(0);
+            let msg_id = fetch.header().and_then(parse_message_id_header);
+            result.insert(uid, msg_id);
+        }
+        Ok(result)
+    }
 }
 
 pub const DEFAULT_BATCH_SIZE: u32 = 30;
@@ -613,6 +646,27 @@ pub fn generate_uid_sequence_hashset(
     result
 }
 
+fn parse_message_id_header(header_bytes: &[u8]) -> Option<String> {
+    let header = std::str::from_utf8(header_bytes).ok()?;
+    for line in header.lines() {
+        if let Some(value) = line
+            .strip_prefix("Message-ID:")
+            .or_else(|| line.strip_prefix("Message-Id:"))
+            .or_else(|| line.strip_prefix("Message-id:"))
+        {
+            // mail_parser strips angle brackets, so we must do the same
+            // to ensure comparisons against the Tantivy index match.
+            let trimmed = value.trim();
+            let stripped = trimmed.strip_prefix('<').unwrap_or(trimmed);
+            let stripped = stripped.strip_suffix('>').unwrap_or(stripped);
+            if !stripped.is_empty() {
+                return Some(stripped.to_string());
+            }
+        }
+    }
+    None
+}
+
 #[cfg(test)]
 mod test {
     use super::*;
@@ -668,4 +722,80 @@ mod test {
         assert_eq!(batches[2].0, "5");
         assert_eq!(batches[2].1, 1);
     }
+
+    // ── parse_message_id_header ─────────────────────────────────────
+
+    #[test]
+    fn parse_standard_message_id() {
+        let header = b"Message-ID: <abc123@example.com>\r\n";
+        assert_eq!(
+            parse_message_id_header(header),
+            Some("abc123@example.com".into())
+        );
+    }
+
+    #[test]
+    fn parse_message_id_lowercase() {
+        let header = b"Message-Id: <foo@bar.com>\r\n";
+        assert_eq!(
+            parse_message_id_header(header),
+            Some("foo@bar.com".into())
+        );
+    }
+
+    #[test]
+    fn parse_message_id_extra_whitespace() {
+        let header = b"Message-ID:   <spaces@test.com>  \r\n";
+        assert_eq!(
+            parse_message_id_header(header),
+            Some("spaces@test.com".into())
+        );
+    }
+
+    #[test]
+    fn parse_empty_message_id_returns_none() {
+        let header = b"Message-ID: <>\r\n";
+        assert_eq!(parse_message_id_header(header), None);
+    }
+
+    #[test]
+    fn parse_missing_header_returns_none() {
+        let header = b"X-Custom: something\r\n";
+        assert_eq!(parse_message_id_header(header), None);
+    }
+
+    #[test]
+    fn parse_empty_body_returns_none() {
+        assert_eq!(parse_message_id_header(b""), None);
+    }
+
+    #[test]
+    fn parse_message_id_in_full_header() {
+        // The Message-ID line is in the middle, not at the start.
+        let header = b"From: sender@example.com\r\n\
+Date: Thu, 01 Jan 2025 00:00:00 +0000\r\n\
+Subject: test\r\n\
+Message-ID: <mid@example.com>\r\n\
+To: recipient@example.com\r\n\r\n";
+        assert_eq!(
+            parse_message_id_header(header),
+            Some("mid@example.com".into())
+        );
+    }
+
+    #[test]
+    fn parse_message_id_only_in_full_header() {
+        // Only a few headers, Message-ID is among them.
+        let header = b"From: a@b.com\r\nMessage-ID: <x@y.com>\r\n\r\n";
+        assert_eq!(parse_message_id_header(header), Some("x@y.com".into()));
+    }
+
+    #[test]
+    fn parse_message_id_no_brackets_still_works() {
+        let header = b"Message-ID: plain@example.com\r\n";
+        assert_eq!(
+            parse_message_id_header(header),
+            Some("plain@example.com".into())
+        );
+    }
 }

crates/core/src/imap/manager.rs

@@ -95,16 +95,40 @@ impl ImapConnectionManager {
 
     pub async fn build(account_id: u64) -> BichonResult<Session<Box<dyn SessionStream>>> {
         let account = AccountModel::get(account_id)?;
-        let client = match Self::create_client(&account).await {
-            Ok(client) => client,
-            Err(error) => {
-                error!(
-                    "Failed to create IMAP {}'s client: {:#?}",
-                    &account.email, error
-                );
-                return Err(error);
+        let account_email = account.email.clone();
+
+        let mut client = None;
+        for attempt in 0..3u32 {
+            match Self::create_client(&account).await {
+                Ok(c) => {
+                    client = Some(c);
+                    break;
+                }
+                Err(error) if error.code() == ErrorCode::NetworkError && attempt < 2 => {
+                    warn!(
+                        "IMAP connection attempt {}/3 to {} failed (network error), retrying...",
+                        attempt + 1,
+                        account_email
+                    );
+                    tokio::time::sleep(std::time::Duration::from_secs(1)).await;
+                    continue;
+                }
+                Err(error) => {
+                    error!(
+                        "Failed to create IMAP {}'s client: {:#?}",
+                        account_email, error
+                    );
+                    return Err(error);
+                }
             }
-        };
+        }
+
+        let client = client.ok_or_else(|| {
+            raise_error!(
+                format!("Failed to create IMAP {}'s client after 3 attempts", account_email),
+                ErrorCode::NetworkError
+            )
+        })?;
 
         let mut session = match Self::authenticate(client, &account).await {
             Ok(session) => session,

crates/core/src/imap/mock_server.rs

@@ -0,0 +1,538 @@
+//
+// Copyright (c) 2025-2026 rustmailer.com (https://rustmailer.com)
+//
+// This file is part of the Bichon Email Archiving Project
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+//! A minimal scriptable IMAP server for integration testing.
+//!
+//! Each instance listens on a random localhost port and responds to a
+//! pre-configured script of (expected_command, response) pairs. Commands
+//! are matched by substring — the first matching pattern wins.
+//!
+//! # Example
+//! ```ignore
+//! let server = MockImapServer::new()
+//!     .greeting("* OK ready\r\n")
+//!     .respond("LOGIN", "A0 OK logged in\r\n")
+//!     .respond("CAPABILITY", "* CAPABILITY IMAP4rev1\r\nA0 OK done\r\n")
+//!     .respond("STATUS", "* STATUS INBOX (MESSAGES 10 UIDVALIDITY 42)\r\nA0 OK\r\n")
+//!     .respond("LOGOUT", "* BYE\r\nA0 OK\r\n")
+//!     .start()
+//!     .await;
+//!
+//! let (host, port) = server.addr();
+//! // connect to host:port with Encryption::None
+//! ```
+
+use std::net::SocketAddr;
+use std::sync::Arc;
+use tokio::io::{AsyncBufReadExt, AsyncWriteExt, BufReader};
+use tokio::net::{TcpListener, TcpStream};
+
+type Response = Vec<u8>;
+
+pub struct MockImapServer {
+    greeting: Vec<u8>,
+    script: Vec<(String, Response)>,
+}
+
+impl MockImapServer {
+    pub fn new() -> Self {
+        Self {
+            greeting: b"* OK Mock IMAP server ready\r\n".to_vec(),
+            script: Vec::new(),
+        }
+    }
+
+    /// Set the greeting banner sent immediately after connection.
+    pub fn greeting(mut self, banner: impl Into<Vec<u8>>) -> Self {
+        self.greeting = banner.into();
+        self
+    }
+
+    /// Add a script step: when a client command *contains* `pattern` (case-insensitive),
+    /// respond with `response`. Steps are checked in insertion order.
+    pub fn respond(mut self, pattern: impl Into<String>, response: impl Into<Vec<u8>>) -> Self {
+        self.script.push((pattern.into(), response.into()));
+        self
+    }
+
+    /// Start the server on a random port. Returns a handle whose `addr()` gives
+    /// the `(host, port)` to connect to.
+    pub async fn start(self) -> MockImapServerHandle {
+        let listener = TcpListener::bind("127.0.0.1:0").await.expect("bind");
+        let addr = listener.local_addr().expect("local_addr");
+
+        let server = Arc::new(self);
+
+        tokio::spawn(async move {
+            loop {
+                match listener.accept().await {
+                    Ok((stream, _)) => {
+                        let srv = server.clone();
+                        tokio::spawn(async move {
+                            srv.handle_connection(stream).await;
+                        });
+                    }
+                    Err(_) => break,
+                }
+            }
+        });
+
+        MockImapServerHandle { addr }
+    }
+
+    async fn handle_connection(&self, mut stream: TcpStream) {
+        let (reader, mut writer) = stream.split();
+        let mut reader = BufReader::new(reader);
+
+        // Send greeting
+        if writer.write_all(&self.greeting).await.is_err() {
+            return;
+        }
+
+        let mut line = String::new();
+        loop {
+            line.clear();
+            match reader.read_line(&mut line).await {
+                Ok(0) => break, // EOF
+                Ok(_) => {}
+                Err(_) => break,
+            }
+
+            let tag = extract_tag(&line).unwrap_or("A0");
+            let matched = self.find_match(&line);
+            if let Some(response) = matched {
+                let substituted = substitute_tag(response, tag);
+                if writer.write_all(&substituted).await.is_err() {
+                    break;
+                }
+            } else {
+                // Default: send tagged OK for commands we don't handle
+                let fallback = format!("{tag} OK done\r\n");
+                if writer.write_all(fallback.as_bytes()).await.is_err() {
+                    break;
+                }
+            }
+        }
+    }
+
+    fn find_match(&self, line: &str) -> Option<&[u8]> {
+        let line_lower = line.to_lowercase();
+        for (pattern, response) in &self.script {
+            if line_lower.contains(&pattern.to_lowercase()) {
+                return Some(response);
+            }
+        }
+        None
+    }
+}
+
+impl Default for MockImapServer {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
+/// Handle to a running mock IMAP server. The server stops when this handle
+/// is dropped.
+pub struct MockImapServerHandle {
+    addr: SocketAddr,
+}
+
+impl MockImapServerHandle {
+    pub fn host(&self) -> String {
+        self.addr.ip().to_string()
+    }
+
+    pub fn port(&self) -> u16 {
+        self.addr.port()
+    }
+}
+
+fn extract_tag(line: &str) -> Option<&str> {
+    line.split_whitespace().next()
+}
+
+/// Replace `{TAG}` placeholders in `response` with `tag`.
+fn substitute_tag(response: &[u8], tag: &str) -> Vec<u8> {
+    let placeholder = b"{TAG}";
+    if response.is_empty() || !contains_slice(response, placeholder) {
+        return response.to_vec();
+    }
+    let tag_bytes = tag.as_bytes();
+    let mut result = Vec::with_capacity(response.len());
+    let mut pos = 0;
+    while let Some(idx) = find_slice(&response[pos..], placeholder) {
+        result.extend_from_slice(&response[pos..pos + idx]);
+        result.extend_from_slice(tag_bytes);
+        pos += idx + placeholder.len();
+    }
+    result.extend_from_slice(&response[pos..]);
+    result
+}
+
+fn contains_slice(haystack: &[u8], needle: &[u8]) -> bool {
+    haystack.windows(needle.len()).any(|w| w == needle)
+}
+
+fn find_slice(haystack: &[u8], needle: &[u8]) -> Option<usize> {
+    haystack
+        .windows(needle.len())
+        .position(|w| w == needle)
+}
+
+// ============================================================
+// Pre-built response helpers
+// ============================================================
+
+/// Build a tagged OK response.
+pub fn ok(tag: impl AsRef<str>, msg: impl AsRef<str>) -> Vec<u8> {
+    format!("{} OK {}\r\n", tag.as_ref(), msg.as_ref()).into_bytes()
+}
+
+/// Build a STATUS response line.
+pub fn status_response(
+    mailbox: &str,
+    messages: u32,
+    unseen: u32,
+    uid_next: u32,
+    uid_validity: Option<u32>,
+) -> Vec<u8> {
+    let uv = uid_validity
+        .map(|v| format!(" UIDVALIDITY {v}"))
+        .unwrap_or_default();
+    let text = format!(
+        "* STATUS \"{mailbox}\" (MESSAGES {messages} UNSEEN {unseen} UIDNEXT {uid_next}{uv})\r\n"
+    );
+    // Clients expect a tagged response after the untagged STATUS line.
+    // We produce a generic OK that works for any tag.
+    let mut out = text.into_bytes();
+    out.extend_from_slice(b"{TAG} OK STATUS completed\r\n");
+    out
+}
+
+/// Build an EXAMINE response with mailbox data.
+pub fn examine_response(
+    _mailbox: &str,
+    exists: u32,
+    uid_validity: u32,
+    uid_next: u32,
+) -> Vec<u8> {
+    format!(
+        "* FLAGS (\\Seen \\Answered \\Flagged \\Deleted \\Draft)\r\n\
+         * OK [PERMANENTFLAGS ()]\r\n\
+         * {exists} EXISTS\r\n\
+         * 0 RECENT\r\n\
+         * OK [UIDVALIDITY {uid_validity}]\r\n\
+         * OK [UIDNEXT {uid_next}]\r\n\
+         * OK [HIGHESTMODSEQ 1]\r\n\
+         {{TAG}} OK [READ-ONLY] EXAMINE completed\r\n"
+    )
+    .into_bytes()
+}
+
+/// Build a UID SEARCH response for the given UID list.
+pub fn uid_search_response(uids: &[u32]) -> Vec<u8> {
+    let uid_str = uids
+        .iter()
+        .map(|u| u.to_string())
+        .collect::<Vec<_>>()
+        .join(" ");
+    format!("* SEARCH {uid_str}\r\n{{TAG}} OK SEARCH completed\r\n").into_bytes()
+}
+
+/// Build a UID FETCH response returning full headers (for BODY[HEADER]).
+/// Each entry: (uid, message_id)
+pub fn uid_fetch_metadata_response(entries: &[(u32, &str)]) -> Vec<u8> {
+    let mut out = Vec::new();
+    for (uid, msg_id) in entries {
+        // Build a minimal header that contains the Message-ID line.
+        let header_data = format!(
+            "From: sender@example.com\r\n\
+To: recipient@example.com\r\n\
+Date: Thu, 01 Jan 2025 00:00:00 +0000\r\n\
+Subject: test\r\n\
+Message-ID: {msg_id}\r\n\r\n"
+        );
+        let header_len = header_data.len();
+        let line = format!(
+            "* {uid} FETCH (UID {uid} BODY[HEADER] {{{header_len}}}\r\n\
+{header_data}\
+)\r\n",
+        );
+        out.extend_from_slice(line.as_bytes());
+    }
+    out.extend_from_slice(b"{TAG} OK FETCH completed\r\n");
+    out
+}
+
+/// Build a UID FETCH RFC822 response with a full email body.
+pub fn uid_fetch_rfc822_response(uid: u32, eml: &[u8]) -> Vec<u8> {
+    let header = format!(
+        "* {uid} FETCH (UID {uid} RFC822 {{{len}}}\r\n",
+        len = eml.len()
+    );
+    let mut out = header.into_bytes();
+    out.extend_from_slice(eml);
+    out.extend_from_slice(b")\r\n{TAG} OK FETCH completed\r\n");
+    out
+}
+
+/// A minimal RFC822 email fixture for testing.
+pub fn minimal_eml(subject: &str, message_id: &str) -> Vec<u8> {
+    format!(
+        "From: sender@example.com\r\n\
+         To: recipient@example.com\r\n\
+         Subject: {subject}\r\n\
+         Message-ID: <{message_id}>\r\n\
+         Date: Thu, 01 Jan 2025 00:00:00 +0000\r\n\
+         MIME-Version: 1.0\r\n\
+         Content-Type: text/plain; charset=utf-8\r\n\
+         \r\n\
+         This is a test email: {subject}.\r\n"
+    )
+    .into_bytes()
+}
+
+// ============================================================
+// Self-tests for the mock server itself
+// ============================================================
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    async fn connect_and_read_greeting(host: &str, port: u16) -> String {
+        let mut stream = TcpStream::connect((host, port)).await.unwrap();
+        let (reader, _writer) = stream.split();
+        let mut reader = BufReader::new(reader);
+        let mut line = String::new();
+        reader.read_line(&mut line).await.unwrap();
+        line
+    }
+
+    async fn send_and_recv(host: &str, port: u16, cmd: &str) -> String {
+        let mut stream = TcpStream::connect((host, port)).await.unwrap();
+        let (reader, mut writer) = stream.split();
+        let mut reader = BufReader::new(reader);
+
+        // Read greeting
+        let mut line = String::new();
+        reader.read_line(&mut line).await.unwrap();
+
+        // Send command
+        writer.write_all(cmd.as_bytes()).await.unwrap();
+        writer.write_all(b"\r\n").await.unwrap();
+
+        // Read response (may be multi-line; read until tagged response)
+        let mut out = String::new();
+        loop {
+            line.clear();
+            reader.read_line(&mut line).await.unwrap();
+            out.push_str(&line);
+            if line.starts_with("A0") || line.starts_with("A1") {
+                break;
+            }
+        }
+        out
+    }
+
+    #[tokio::test]
+    async fn test_mock_greeting() {
+        let handle = MockImapServer::new().start().await;
+        let greeting = connect_and_read_greeting(&handle.host(), handle.port()).await;
+        assert!(greeting.starts_with("* OK"));
+    }
+
+    #[tokio::test]
+    async fn test_mock_scripted_response() {
+        let handle = MockImapServer::new()
+            .respond(
+                "LOGIN",
+                "A0 OK LOGIN completed\r\n",
+            )
+            .start()
+            .await;
+
+        let resp = send_and_recv(&handle.host(), handle.port(), "A0 LOGIN u p").await;
+        assert!(resp.contains("LOGIN completed"));
+    }
+
+    #[tokio::test]
+    async fn test_mock_fallback_on_unmatched() {
+        let handle = MockImapServer::new().start().await;
+
+        // Send a command that has no scripted response
+        let resp = send_and_recv(&handle.host(), handle.port(), "A0 NOOP").await;
+        assert!(resp.contains("OK done"), "unmatched command should get fallback OK");
+    }
+
+    #[tokio::test]
+    async fn test_status_response_helper() {
+        let resp = status_response("INBOX", 10, 2, 11, Some(42));
+        let text = String::from_utf8(resp).unwrap();
+        assert!(text.contains("MESSAGES 10"));
+        assert!(text.contains("UNSEEN 2"));
+        assert!(text.contains("UIDNEXT 11"));
+        assert!(text.contains("UIDVALIDITY 42"));
+    }
+
+    #[tokio::test]
+    async fn test_status_response_without_uidvalidity() {
+        let resp = status_response("INBOX", 10, 2, 11, None);
+        let text = String::from_utf8(resp).unwrap();
+        assert!(!text.contains("UIDVALIDITY"));
+        assert!(text.contains("MESSAGES 10"));
+    }
+
+    #[tokio::test]
+    async fn test_examine_response() {
+        let resp = examine_response("INBOX", 10, 42, 11);
+        let text = String::from_utf8(resp).unwrap();
+        assert!(text.contains("UIDVALIDITY 42"));
+        assert!(text.contains("10 EXISTS"));
+    }
+
+    #[tokio::test]
+    async fn test_uid_search_response() {
+        let resp = uid_search_response(&[1, 3, 5]);
+        let text = String::from_utf8(resp).unwrap();
+        assert!(text.contains("SEARCH 1 3 5"));
+    }
+
+    #[tokio::test]
+    async fn test_uid_fetch_metadata_response() {
+        let resp = uid_fetch_metadata_response(&[(1, "msg-a@x.com"), (2, "msg-b@x.com")]);
+        let text = String::from_utf8(resp).unwrap();
+        assert!(text.contains("Message-ID: msg-a@x.com"));
+        assert!(text.contains("Message-ID: msg-b@x.com"));
+    }
+
+    #[tokio::test]
+    async fn test_multiple_commands_in_sequence() {
+        let handle = MockImapServer::new()
+            .respond("LOGIN", "A0 OK LOGIN\r\n")
+            .respond("STATUS", status_response("INBOX", 5, 1, 6, Some(99)))
+            .respond("LOGOUT", "* BYE\r\nA0 OK\r\n")
+            .start()
+            .await;
+
+        let mut stream = TcpStream::connect((handle.host(), handle.port()))
+            .await
+            .unwrap();
+        let (reader, mut writer) = stream.split();
+        let mut reader = BufReader::new(reader);
+
+        // Read greeting
+        let mut buf = String::new();
+        reader.read_line(&mut buf).await.unwrap();
+
+        // LOGIN
+        writer.write_all(b"A0 LOGIN u p\r\n").await.unwrap();
+        buf.clear();
+        reader.read_line(&mut buf).await.unwrap();
+        assert!(buf.contains("LOGIN"));
+
+        // STATUS
+        writer
+            .write_all(b"A0 STATUS INBOX (MESSAGES UNSEEN UIDNEXT UIDVALIDITY)\r\n")
+            .await
+            .unwrap();
+        buf.clear();
+        // Read multi-line STATUS response (untagged line + tagged OK)
+        loop {
+            reader.read_line(&mut buf).await.unwrap();
+            if buf.contains("UIDVALIDITY 99") {
+                // Consume the tagged OK line that follows
+                buf.clear();
+                reader.read_line(&mut buf).await.unwrap();
+                break;
+            }
+        }
+
+        // LOGOUT
+        writer.write_all(b"A0 LOGOUT\r\n").await.unwrap();
+        buf.clear();
+        reader.read_line(&mut buf).await.unwrap();
+        assert!(buf.contains("BYE"));
+    }
+
+    #[tokio::test]
+    async fn test_tag_substitution_in_response() {
+        // Use {TAG} placeholder in the response and verify it gets the
+        // client's actual tag ("A5") substituted in.
+        let handle = MockImapServer::new()
+            .respond("LOGIN", "{TAG} OK LOGIN succeeded\r\n")
+            .start()
+            .await;
+
+        let mut stream = TcpStream::connect((handle.host(), handle.port()))
+            .await
+            .unwrap();
+        let (reader, mut writer) = stream.split();
+        let mut reader = BufReader::new(reader);
+
+        // Read greeting
+        let mut buf = String::new();
+        reader.read_line(&mut buf).await.unwrap();
+
+        // Send LOGIN with non-standard tag
+        writer.write_all(b"A5 LOGIN u p\r\n").await.unwrap();
+        buf.clear();
+        reader.read_line(&mut buf).await.unwrap();
+
+        assert!(
+            buf.contains("A5 OK LOGIN succeeded"),
+            "expected 'A5 OK LOGIN succeeded', got '{buf}'"
+        );
+    }
+
+    #[tokio::test]
+    async fn test_tag_substitution_multiple_placeholders() {
+        let handle = MockImapServer::new()
+            .respond("NOOP", "* 0 RECENT\r\n{TAG} OK NOOP done\r\n")
+            .start()
+            .await;
+
+        let mut stream = TcpStream::connect((handle.host(), handle.port()))
+            .await
+            .unwrap();
+        let (reader, mut writer) = stream.split();
+        let mut reader = BufReader::new(reader);
+
+        // Read greeting
+        let mut buf = String::new();
+        reader.read_line(&mut buf).await.unwrap();
+
+        // Send with tag "B99"
+        writer.write_all(b"B99 NOOP\r\n").await.unwrap();
+
+        // Read all lines
+        let mut all = String::new();
+        loop {
+            buf.clear();
+            reader.read_line(&mut buf).await.unwrap();
+            all.push_str(&buf);
+            if buf.starts_with("B99") {
+                break;
+            }
+        }
+
+        assert!(all.contains("* 0 RECENT\r\n"));
+        assert!(all.contains("B99 OK NOOP done\r\n"));
+    }
+}

crates/core/src/imap/mod.rs

@@ -26,3 +26,5 @@ pub mod session;
 pub mod stats;
 #[cfg(test)]
 mod tests;
+#[cfg(test)]
+pub mod mock_server;

crates/core/src/store/tantivy/envelope.rs

@@ -278,6 +278,80 @@ impl IndexManager {
         Box::new(boolean_query)
     }
 
+    /// Return all Message-IDs stored in Tantivy for a given mailbox.
+    /// Prefer `mailbox_contains_message_id` for existence checks on large
+    /// mailboxes — this method loads everything into a HashSet.
+    pub fn get_message_ids_for_mailbox(
+        &self,
+        account_id: u64,
+        mailbox_id: u64,
+    ) -> BichonResult<HashSet<String>> {
+        let query = self.mailbox_query(account_id, mailbox_id);
+        let fields = SchemaTools::email_fields();
+        let searcher = self.create_searcher()?;
+
+        let docs = searcher
+            .search(&query, &DocSetCollector)
+            .map_err(|e| raise_error!(format!("{:#?}", e), ErrorCode::InternalError))?;
+
+        let mut result = HashSet::new();
+        for doc_address in docs {
+            let doc = searcher
+                .doc::<TantivyDocument>(doc_address)
+                .map_err(|e| raise_error!(format!("{:#?}", e), ErrorCode::InternalError))?;
+
+            if let Some(v) = doc.get_first(fields.f_message_id) {
+                if let Some(s) = v.as_str() {
+                    if !s.is_empty() {
+                        result.insert(s.to_string());
+                    }
+                }
+            }
+        }
+        Ok(result)
+    }
+
+    /// Check whether a specific Message-ID exists in a mailbox.
+    /// Uses a TermQuery — O(1) per call, no allocation proportional to
+    /// mailbox size. Suitable for large mailboxes where
+    /// `get_message_ids_for_mailbox` would allocate too much memory.
+    pub fn mailbox_contains_message_id(
+        &self,
+        account_id: u64,
+        mailbox_id: u64,
+        message_id: &str,
+    ) -> BichonResult<bool> {
+        let fields = SchemaTools::email_fields();
+        let query = BooleanQuery::new(vec![
+            (
+                Occur::Must,
+                Box::new(TermQuery::new(
+                    Term::from_field_u64(fields.f_account_id, account_id),
+                    IndexRecordOption::Basic,
+                )),
+            ),
+            (
+                Occur::Must,
+                Box::new(TermQuery::new(
+                    Term::from_field_u64(fields.f_mailbox_id, mailbox_id),
+                    IndexRecordOption::Basic,
+                )),
+            ),
+            (
+                Occur::Must,
+                Box::new(TermQuery::new(
+                    Term::from_field_text(fields.f_message_id, message_id),
+                    IndexRecordOption::Basic,
+                )),
+            ),
+        ]);
+        let searcher = self.create_searcher()?;
+        let count = searcher
+            .search(&query, &Count)
+            .map_err(|e| raise_error!(format!("{:#?}", e), ErrorCode::InternalError))?;
+        Ok(count > 0)
+    }
+
     fn envelope_query(&self, account_id: u64, eid: &str) -> Box<dyn Query> {
         let account_id_query = TermQuery::new(
             Term::from_field_u64(SchemaTools::email_fields().f_account_id, account_id),
@@ -2069,4 +2143,362 @@ mod tests {
             "body should be absent when EML is missing"
         );
     }
+
+    // ── get_message_ids_for_mailbox ─────────────────────────────────
+
+    #[test]
+    fn get_message_ids_returns_stored_ids() {
+        let f = SchemaTools::email_fields();
+        let index = Index::create_in_ram(SchemaTools::email_schema());
+        index.tokenizers().register("euro", EuroTokenizer::new());
+
+        // Insert two docs for mailbox 10, one for mailbox 20
+        {
+            let mut writer = index
+                .writer_with_num_threads(1, 15_000_000)
+                .expect("writer");
+
+            let mut doc1 = TantivyDocument::new();
+            doc1.add_u64(f.f_account_id, 1);
+            doc1.add_u64(f.f_mailbox_id, 10);
+            doc1.add_text(f.f_message_id, "<msg-a@test>");
+            doc1.add_text(f.f_id, "id-a");
+            doc1.add_u64(f.f_uid, 1);
+            doc1.add_text(f.f_content_hash, "hash-a");
+            writer.add_document(doc1).unwrap();
+
+            let mut doc2 = TantivyDocument::new();
+            doc2.add_u64(f.f_account_id, 1);
+            doc2.add_u64(f.f_mailbox_id, 10);
+            doc2.add_text(f.f_message_id, "<msg-b@test>");
+            doc2.add_text(f.f_id, "id-b");
+            doc2.add_u64(f.f_uid, 2);
+            doc2.add_text(f.f_content_hash, "hash-b");
+            writer.add_document(doc2).unwrap();
+
+            let mut doc3 = TantivyDocument::new();
+            doc3.add_u64(f.f_account_id, 1);
+            doc3.add_u64(f.f_mailbox_id, 20);
+            doc3.add_text(f.f_message_id, "<msg-c@test>");
+            doc3.add_text(f.f_id, "id-c");
+            doc3.add_u64(f.f_uid, 3);
+            doc3.add_text(f.f_content_hash, "hash-c");
+            writer.add_document(doc3).unwrap();
+
+            writer.commit().unwrap();
+        }
+
+        let reader = index.reader().unwrap();
+        reader.reload().unwrap();
+        let searcher = reader.searcher();
+
+        // We can't easily call ENVELOPE_MANAGER.get_message_ids_for_mailbox
+        // because it reads from ENVELOPE_MANAGER's own index, not our in-memory one.
+        // Instead, test the query pattern directly.
+        let query: Box<dyn Query> = {
+            let account_query = TermQuery::new(
+                Term::from_field_u64(f.f_account_id, 1),
+                IndexRecordOption::Basic,
+            );
+            let mailbox_query = TermQuery::new(
+                Term::from_field_u64(f.f_mailbox_id, 10),
+                IndexRecordOption::Basic,
+            );
+            Box::new(BooleanQuery::new(vec![
+                (Occur::Must, Box::new(account_query)),
+                (Occur::Must, Box::new(mailbox_query)),
+            ]))
+        };
+
+        let docs = searcher
+            .search(&query, &DocSetCollector)
+            .unwrap();
+
+        let mut ids: Vec<String> = Vec::new();
+        for addr in docs {
+            let doc: TantivyDocument = searcher.doc(addr).unwrap();
+            if let Some(v) = doc.get_first(f.f_message_id) {
+                if let Some(s) = v.as_str() {
+                    ids.push(s.to_string());
+                }
+            }
+        }
+        ids.sort();
+
+        assert_eq!(ids, vec!["<msg-a@test>", "<msg-b@test>"]);
+    }
+
+    #[test]
+    fn get_message_ids_empty_mailbox_returns_empty() {
+        let f = SchemaTools::email_fields();
+        let index = Index::create_in_ram(SchemaTools::email_schema());
+        index.tokenizers().register("euro", EuroTokenizer::new());
+
+        {
+            let mut writer = index
+                .writer_with_num_threads(1, 15_000_000)
+                .expect("writer");
+
+            // Doc for a different mailbox
+            let mut doc = TantivyDocument::new();
+            doc.add_u64(f.f_account_id, 1);
+            doc.add_u64(f.f_mailbox_id, 99);
+            doc.add_text(f.f_message_id, "<other@test>");
+            doc.add_text(f.f_id, "id-other");
+            doc.add_u64(f.f_uid, 1);
+            doc.add_text(f.f_content_hash, "hash-other");
+            writer.add_document(doc).unwrap();
+            writer.commit().unwrap();
+        }
+
+        let reader = index.reader().unwrap();
+        reader.reload().unwrap();
+        let searcher = reader.searcher();
+
+        let query: Box<dyn Query> = {
+            let account_query = TermQuery::new(
+                Term::from_field_u64(f.f_account_id, 1),
+                IndexRecordOption::Basic,
+            );
+            let mailbox_query = TermQuery::new(
+                Term::from_field_u64(f.f_mailbox_id, 10),
+                IndexRecordOption::Basic,
+            );
+            Box::new(BooleanQuery::new(vec![
+                (Occur::Must, Box::new(account_query)),
+                (Occur::Must, Box::new(mailbox_query)),
+            ]))
+        };
+
+        let docs = searcher.search(&query, &DocSetCollector).unwrap();
+        assert!(docs.is_empty());
+    }
+
+    // ── mailbox_contains_message_id ───────────────────────────────
+
+    #[test]
+    fn mailbox_contains_message_id_finds_existing() {
+        let f = SchemaTools::email_fields();
+        let index = Index::create_in_ram(SchemaTools::email_schema());
+        index.tokenizers().register("euro", EuroTokenizer::new());
+
+        {
+            let mut writer = index
+                .writer_with_num_threads(1, 15_000_000)
+                .expect("writer");
+
+            let mut doc = TantivyDocument::new();
+            doc.add_u64(f.f_account_id, 1);
+            doc.add_u64(f.f_mailbox_id, 10);
+            doc.add_text(f.f_message_id, "abc@example.com");
+            doc.add_text(f.f_id, "id-1");
+            doc.add_u64(f.f_uid, 1);
+            doc.add_text(f.f_content_hash, "hash-1");
+            writer.add_document(doc).unwrap();
+            writer.commit().unwrap();
+        }
+
+        // We test the query pattern directly (can't call ENVELOPE_MANAGER
+        // which uses a different index).
+        let reader = index.reader().unwrap();
+        reader.reload().unwrap();
+        let searcher = reader.searcher();
+
+        let query = BooleanQuery::new(vec![
+            (
+                Occur::Must,
+                Box::new(TermQuery::new(
+                    Term::from_field_u64(f.f_account_id, 1),
+                    IndexRecordOption::Basic,
+                )),
+            ),
+            (
+                Occur::Must,
+                Box::new(TermQuery::new(
+                    Term::from_field_u64(f.f_mailbox_id, 10),
+                    IndexRecordOption::Basic,
+                )),
+            ),
+            (
+                Occur::Must,
+                Box::new(TermQuery::new(
+                    Term::from_field_text(f.f_message_id, "abc@example.com"),
+                    IndexRecordOption::Basic,
+                )),
+            ),
+        ]);
+
+        let count = searcher.search(&query, &Count).unwrap();
+        assert_eq!(count, 1);
+    }
+
+    #[test]
+    fn mailbox_contains_message_id_returns_zero_for_missing() {
+        let f = SchemaTools::email_fields();
+        let index = Index::create_in_ram(SchemaTools::email_schema());
+        index.tokenizers().register("euro", EuroTokenizer::new());
+
+        {
+            let mut writer = index
+                .writer_with_num_threads(1, 15_000_000)
+                .expect("writer");
+
+            let mut doc = TantivyDocument::new();
+            doc.add_u64(f.f_account_id, 1);
+            doc.add_u64(f.f_mailbox_id, 10);
+            doc.add_text(f.f_message_id, "existing@example.com");
+            doc.add_text(f.f_id, "id-1");
+            doc.add_u64(f.f_uid, 1);
+            doc.add_text(f.f_content_hash, "hash-1");
+            writer.add_document(doc).unwrap();
+            writer.commit().unwrap();
+        }
+
+        let reader = index.reader().unwrap();
+        reader.reload().unwrap();
+        let searcher = reader.searcher();
+
+        let query = BooleanQuery::new(vec![
+            (
+                Occur::Must,
+                Box::new(TermQuery::new(
+                    Term::from_field_u64(f.f_account_id, 1),
+                    IndexRecordOption::Basic,
+                )),
+            ),
+            (
+                Occur::Must,
+                Box::new(TermQuery::new(
+                    Term::from_field_u64(f.f_mailbox_id, 10),
+                    IndexRecordOption::Basic,
+                )),
+            ),
+            (
+                Occur::Must,
+                Box::new(TermQuery::new(
+                    Term::from_field_text(f.f_message_id, "nonexistent@example.com"),
+                    IndexRecordOption::Basic,
+                )),
+            ),
+        ]);
+
+        let count = searcher.search(&query, &Count).unwrap();
+        assert_eq!(count, 0);
+    }
+
+    #[test]
+    fn mailbox_contains_message_id_respects_mailbox_boundary() {
+        let f = SchemaTools::email_fields();
+        let index = Index::create_in_ram(SchemaTools::email_schema());
+        index.tokenizers().register("euro", EuroTokenizer::new());
+
+        {
+            let mut writer = index
+                .writer_with_num_threads(1, 15_000_000)
+                .expect("writer");
+
+            // Same Message-ID in mailbox 10
+            let mut doc1 = TantivyDocument::new();
+            doc1.add_u64(f.f_account_id, 1);
+            doc1.add_u64(f.f_mailbox_id, 10);
+            doc1.add_text(f.f_message_id, "shared@example.com");
+            doc1.add_text(f.f_id, "id-1");
+            doc1.add_u64(f.f_uid, 1);
+            doc1.add_text(f.f_content_hash, "hash-1");
+            writer.add_document(doc1).unwrap();
+
+            // Same Message-ID in mailbox 20 (different mailbox)
+            let mut doc2 = TantivyDocument::new();
+            doc2.add_u64(f.f_account_id, 1);
+            doc2.add_u64(f.f_mailbox_id, 20);
+            doc2.add_text(f.f_message_id, "shared@example.com");
+            doc2.add_text(f.f_id, "id-2");
+            doc2.add_u64(f.f_uid, 2);
+            doc2.add_text(f.f_content_hash, "hash-2");
+            writer.add_document(doc2).unwrap();
+            writer.commit().unwrap();
+        }
+
+        let reader = index.reader().unwrap();
+        reader.reload().unwrap();
+        let searcher = reader.searcher();
+
+        // Query mailbox 10: should find 1
+        let q10 = BooleanQuery::new(vec![
+            (
+                Occur::Must,
+                Box::new(TermQuery::new(
+                    Term::from_field_u64(f.f_account_id, 1),
+                    IndexRecordOption::Basic,
+                )),
+            ),
+            (
+                Occur::Must,
+                Box::new(TermQuery::new(
+                    Term::from_field_u64(f.f_mailbox_id, 10),
+                    IndexRecordOption::Basic,
+                )),
+            ),
+            (
+                Occur::Must,
+                Box::new(TermQuery::new(
+                    Term::from_field_text(f.f_message_id, "shared@example.com"),
+                    IndexRecordOption::Basic,
+                )),
+            ),
+        ]);
+        assert_eq!(searcher.search(&q10, &Count).unwrap(), 1);
+
+        // Query mailbox 20: should find 1
+        let q20 = BooleanQuery::new(vec![
+            (
+                Occur::Must,
+                Box::new(TermQuery::new(
+                    Term::from_field_u64(f.f_account_id, 1),
+                    IndexRecordOption::Basic,
+                )),
+            ),
+            (
+                Occur::Must,
+                Box::new(TermQuery::new(
+                    Term::from_field_u64(f.f_mailbox_id, 20),
+                    IndexRecordOption::Basic,
+                )),
+            ),
+            (
+                Occur::Must,
+                Box::new(TermQuery::new(
+                    Term::from_field_text(f.f_message_id, "shared@example.com"),
+                    IndexRecordOption::Basic,
+                )),
+            ),
+        ]);
+        assert_eq!(searcher.search(&q20, &Count).unwrap(), 1);
+
+        // Query mailbox 99 (no docs): should find 0
+        let q99 = BooleanQuery::new(vec![
+            (
+                Occur::Must,
+                Box::new(TermQuery::new(
+                    Term::from_field_u64(f.f_account_id, 1),
+                    IndexRecordOption::Basic,
+                )),
+            ),
+            (
+                Occur::Must,
+                Box::new(TermQuery::new(
+                    Term::from_field_u64(f.f_mailbox_id, 99),
+                    IndexRecordOption::Basic,
+                )),
+            ),
+            (
+                Occur::Must,
+                Box::new(TermQuery::new(
+                    Term::from_field_text(f.f_message_id, "shared@example.com"),
+                    IndexRecordOption::Basic,
+                )),
+            ),
+        ]);
+        assert_eq!(searcher.search(&q99, &Count).unwrap(), 0);
+    }
 }