test: drive a real Bot against a stand-in API

Every test went through `MockSender`, so `media_sender`'s `Bot` implementation — the URL it builds, the multipart it sends, the per-chat limiter and the bot-wide budget it charges — was never exercised, and neither was any handler reached from a real update. The two things that made that hard are gone: - `media_sender::test_support::fake_api::FakeApi` is a stand-in for `api.telegram.org`: a `tokio` TCP listener that reads one HTTP/1.1 request (JSON or multipart), records it and answers the smallest result the method needs. No new dependency, and `Bot::new(token).set_api_url(api.url())` points a real `Bot` at it. Note for future tests: teloxide keys methods by payload type, so the path is `SendMediaGroup`, not `sendMediaGroup`. - `message_handler` built its own `AppContext::from_statics` internally, so no test could reach its branches; its body is now `handle_message(ctx, bot, message)` with `message_handler` as the thin `dptree` entry. Tests: a media group through the real `Bot` (asserting the multipart fields — chat, media URL, caption — and that the send charged the chat's limiter), the forward button through the real callback path (`CopyMessages`, `DeleteMessage`, `AnswerCallbackQuery` with the prompt's ids and the toast text), and `handle_message` twice (a prompt reply becoming an `EditMessageCaption`, and a supported link in a group producing the one explanatory `SendMessage`). Also closes the redirect-hop gap left open by the download guard: the live `a_redirect_into_the_hosts_network_is_refused` follows a public redirector to `169.254.169.254` and asserts the policy refuses the hop (verified against httpbin.org here, and by mutation — disabling the hop check fails it). Docs: AGENTS.md's testing conventions and untested-modules list (the Bot implementation and the handler branches are covered now; `main.rs`'s startup/shutdown and its `dptree` tree still are not). `cargo fmt`, `cargo clippy --workspace --all-targets --locked -- -D warnings`, `cargo test --workspace --locked` (201 passed, 16 ignored) clean.
2026-09-23 23:32:05 +00:00 · 2026-09-21 03:02:43 +08:00
parent cd8b5ac67b
commit 4e723e1657
7 changed files with 369 additions and 14 deletions
@@ -216,7 +216,7 @@ async fn handle_callback(
 #[cfg(test)]
 mod tests {
    use super::*;
-    use crate::ctx::test_support::{PROMPT_ID, TestStores, api_error, seed_prompt};
+    use crate::ctx::test_support::{FORWARDED_ID, PROMPT_ID, TestStores, api_error, seed_prompt};
    use crate::media_sender::test_support::{MockSender, Outcome};

    /// The Telegram wording the mocks answer with: a chat the bot cannot reach.
@@ -315,6 +315,33 @@ mod tests {
        );
    }

+    /// The whole callback path against a stand-in API through a real `Bot`:
+    /// copy, delete, toast, carrying the ids the prompt held. The scripted
+    /// mock records that a call happened; this records what the API received.
+    #[tokio::test]
+    async fn the_forward_button_talks_to_the_api_through_a_real_bot() {
+        use crate::media_sender::test_support::fake_api::FakeApi;
+        use teloxide::Bot;
+
+        let api = FakeApi::start().await;
+        let bot = Bot::new("42:TEST").set_api_url(api.url());
+        let stores = TestStores::new();
+        let ctx = stores.ctx(&bot);
+        seed_prompt(&ctx, "", crate::db::unix_now()).await;
+
+        handle_callback(&ctx, callback_id(), 1, PROMPT_ID, "forward").await;
+
+        assert_eq!(
+            api.methods(),
+            vec!["CopyMessages", "DeleteMessage", "AnswerCallbackQuery"]
+        );
+        let copy = api.body("CopyMessages");
+        assert_eq!(copy["chat_id"], 2, "the prompt's channel");
+        assert_eq!(copy["from_chat_id"], 1);
+        assert_eq!(copy["message_ids"], serde_json::json!([FORWARDED_ID]));
+        assert_eq!(api.body("AnswerCallbackQuery")["text"], "✅ Forwarded");
+    }
+
    #[tokio::test]
    async fn forward_without_a_channel_is_reported() {
        let sender = MockSender::scripted(vec![], || api_error(API_ERROR));
@@ -181,7 +181,21 @@ async fn edit_message_handler(
    true
 }

+/// The `dptree` entry point: the process-wide context, plus the bot the
+/// dispatcher handed us (used for the replies this module sends itself).
 pub async fn message_handler(bot: Bot, message: Message) -> Result<(), RequestError> {
+    handle_message(&AppContext::from_statics(&bot), &bot, message).await
+}
+
+/// Body of [`message_handler`], taking its context. Every branch here — the
+/// edit-reply interception, the command path, the private-chat link enqueue and
+/// the group hint — is otherwise reachable only through the process-wide
+/// statics, which is why none of them had a test.
+pub(crate) async fn handle_message(
+    ctx: &AppContext<'_>,
+    bot: &Bot,
+    message: Message,
+) -> Result<(), RequestError> {
    let is_private = matches!(message.chat.kind, ChatKind::Private(_));
    let sender = message
        .from
@@ -207,13 +221,7 @@ pub async fn message_handler(bot: Bot, message: Message) -> Result<(), RequestEr
    if is_private
        && let Some(reply) = message.reply_to_message()
        && let Some(text) = message.text()
-        && edit_message_handler(
-            &AppContext::from_statics(&bot),
-            message.chat.id.0,
-            reply.id.0 as i64,
-            text,
-        )
-        .await
+        && edit_message_handler(ctx, message.chat.id.0, reply.id.0 as i64, text).await
    {
        return respond(());
    }
@@ -228,7 +236,7 @@ pub async fn message_handler(bot: Bot, message: Message) -> Result<(), RequestEr
            text.split_whitespace().next().unwrap_or("<empty>")
        );
        log::trace!("command text: {text_preview}");
-        execute_command(&bot, &message, command).await?;
+        execute_command(bot, &message, command).await?;
        return respond(());
    }
    if is_private {
@@ -262,7 +270,7 @@ pub async fn message_handler(bot: Bot, message: Message) -> Result<(), RequestEr
        // the expectation is there). Unsupported links stay ignored; the hint
        // names the two paths that do work. Channels are excluded — the reply
        // would be posted into the channel itself.
-        let _ = reply(&bot, message.chat.id.0, message.id, GROUP_LINK_HINT).await;
+        let _ = reply(ctx.sender, message.chat.id.0, message.id, GROUP_LINK_HINT).await;
    }
    respond(())
 }
@@ -287,7 +295,7 @@ fn is_group(kind: &ChatKind) -> bool {
 #[cfg(test)]
 mod tests {
    use super::*;
-    use crate::ctx::test_support::{PROMPT_ID, TestStores, api_error, seed_prompt};
+    use crate::ctx::test_support::{FORWARDED_ID, PROMPT_ID, TestStores, api_error, seed_prompt};
    use crate::media_sender::test_support::{MockSender, Outcome};
    use teloxide::RequestError;

@@ -393,6 +401,64 @@ mod tests {
        assert!(sender.calls().is_empty());
    }

+    /// A reply driven through the real message entry point into a real `Bot`:
+    /// the routing (reply-to-prompt → caption swap, before the command and URL
+    /// branches) and the request teloxide builds.
+    #[tokio::test]
+    async fn a_prompt_reply_reaches_the_api_as_a_caption_edit() {
+        use crate::media_sender::test_support::fake_api::FakeApi;
+        use teloxide::Bot;
+
+        let api = FakeApi::start().await;
+        let bot = Bot::new("42:TEST").set_api_url(api.url());
+        let stores = TestStores::new();
+        let ctx = stores.ctx(&bot);
+        seed_prompt(&ctx, "", crate::db::unix_now()).await;
+        let message: Message = serde_json::from_value(serde_json::json!({
+            "message_id": PROMPT_ID + 1,
+            "date": 0,
+            "chat": { "id": 1, "type": "private" },
+            "from": { "id": 5, "is_bot": false, "first_name": "u" },
+            "reply_to_message": {
+                "message_id": PROMPT_ID,
+                "date": 0,
+                "chat": { "id": 1, "type": "private" },
+                "text": "prompt",
+            },
+            "text": "new caption",
+        }))
+        .expect("a minimal message deserializes");
+
+        handle_message(&ctx, &bot, message).await.unwrap();
+
+        assert_eq!(api.methods(), vec!["EditMessageCaption"]);
+        let body = api.body("EditMessageCaption");
+        assert_eq!(body["chat_id"], 1);
+        assert_eq!(body["message_id"], FORWARDED_ID);
+        assert_eq!(
+            body["caption"],
+            "<a href=\"https://x.com/u/status/1\">new caption</a>"
+        );
+
+        // The other branch of the same entry point: a supported link in a group
+        // gets the one explanatory reply (the link pipeline is private-chat only,
+        // and dropping it in silence reads as a broken bot).
+        let group: Message = serde_json::from_value(serde_json::json!({
+            "message_id": 2,
+            "date": 0,
+            "chat": { "id": -100, "type": "group", "title": "g" },
+            "from": { "id": 5, "is_bot": false, "first_name": "u" },
+            "text": "https://x.com/u/status/1",
+            "entities": [{ "type": "url", "offset": 0, "length": 24 }],
+        }))
+        .expect("a minimal group message deserializes");
+
+        handle_message(&ctx, &bot, group).await.unwrap();
+
+        assert_eq!(api.methods(), vec!["EditMessageCaption", "SendMessage"]);
+        assert_eq!(api.body("SendMessage")["text"], GROUP_LINK_HINT);
+    }
+
    #[test]
    fn the_link_hint_is_for_groups_only() {
        use teloxide::types::{ChatPrivate, ChatPublic, PublicChatChannel, PublicChatSupergroup};
@@ -280,6 +280,200 @@ pub(crate) mod test_support {
        EditErr,
    }

+    /// A stand-in for `api.telegram.org` for the tests that must drive a real
+    /// `Bot` — its request building, the per-chat limiter, the bot-wide budget
+    /// — which the scripted mock bypasses entirely. Records every call and
+    /// answers the smallest result each method needs.
+    pub(crate) mod fake_api {
+        use parking_lot::Mutex;
+        use std::sync::Arc;
+        use tokio::io::{AsyncReadExt, AsyncWriteExt};
+        use tokio::net::{TcpListener, TcpStream};
+
+        pub(crate) struct FakeApi {
+            url: url::Url,
+            calls: Arc<Mutex<Vec<(String, serde_json::Value)>>>,
+            server: tokio::task::JoinHandle<()>,
+        }
+
+        impl FakeApi {
+            /// Binds an ephemeral port and serves until dropped.
+            pub(crate) async fn start() -> FakeApi {
+                let listener = TcpListener::bind("127.0.0.1:0").await.unwrap();
+                let addr = listener.local_addr().unwrap();
+                let calls = Arc::new(Mutex::new(Vec::new()));
+                let recorded = Arc::clone(&calls);
+                let server = tokio::spawn(async move {
+                    while let Ok((mut socket, _)) = listener.accept().await {
+                        let recorded = Arc::clone(&recorded);
+                        tokio::spawn(async move {
+                            let Some((method, body)) = read_request(&mut socket).await else {
+                                return;
+                            };
+                            recorded.lock().push((method.clone(), body));
+                            let payload = serde_json::json!({
+                                "ok": true,
+                                "result": canned_result(&method),
+                            })
+                            .to_string();
+                            let response = format!(
+                                "HTTP/1.1 200 OK\r\ncontent-type: application/json\r\n\
+                                 content-length: {}\r\nconnection: close\r\n\r\n{}",
+                                payload.len(),
+                                payload
+                            );
+                            let _ = socket.write_all(response.as_bytes()).await;
+                            let _ = socket.flush().await;
+                        });
+                    }
+                });
+                FakeApi {
+                    // Trailing slash: teloxide appends `bot<token>/<method>`.
+                    url: url::Url::parse(&format!("http://{addr}/")).unwrap(),
+                    calls,
+                    server,
+                }
+            }
+
+            /// Where to point a `Bot`: `Bot::new(token).set_api_url(api.url())`.
+            pub(crate) fn url(&self) -> url::Url {
+                self.url.clone()
+            }
+
+            /// Method names in call order.
+            pub(crate) fn methods(&self) -> Vec<String> {
+                self.calls.lock().iter().map(|(m, _)| m.clone()).collect()
+            }
+
+            /// The JSON body of the first call to `method` (`Null` for a body
+            /// that is not JSON, i.e. a multipart upload).
+            pub(crate) fn body(&self, method: &str) -> serde_json::Value {
+                self.calls
+                    .lock()
+                    .iter()
+                    .find(|(m, _)| m == method)
+                    .map(|(_, body)| body.clone())
+                    .unwrap_or(serde_json::Value::Null)
+            }
+        }
+
+        impl Drop for FakeApi {
+            fn drop(&mut self) {
+                self.server.abort();
+            }
+        }
+
+        /// The smallest result teloxide can deserialize for a method. The names
+        /// arrive as the payload type's own — `SendMediaGroup`, not
+        /// `sendMediaGroup`: teloxide builds the URL from that, and the Bot API
+        /// accepts the spelling.
+        fn canned_result(method: &str) -> serde_json::Value {
+            match method {
+                "CopyMessages" => serde_json::json!([{ "message_id": 11 }]),
+                "SendMediaGroup" => serde_json::json!([minimal_message()]),
+                "SendMessage" | "SendAnimation" | "EditMessageCaption" => minimal_message(),
+                _ => serde_json::Value::Bool(true),
+            }
+        }
+
+        fn minimal_message() -> serde_json::Value {
+            serde_json::json!({
+                "message_id": 1,
+                "date": 0,
+                "chat": { "id": 1, "type": "private" },
+            })
+        }
+
+        /// One HTTP/1.1 request: the head up to the blank line, then
+        /// `content-length` bytes of body — JSON for most methods, multipart
+        /// for the media ones (teloxide sends `SendMediaGroup` that way).
+        async fn read_request(socket: &mut TcpStream) -> Option<(String, serde_json::Value)> {
+            let mut buf = Vec::new();
+            let mut chunk = [0u8; 4096];
+            loop {
+                let n = socket.read(&mut chunk).await.ok()?;
+                if n == 0 {
+                    return None;
+                }
+                buf.extend_from_slice(&chunk[..n]);
+                let Some(headers_end) = find(&buf, b"\r\n\r\n") else {
+                    continue;
+                };
+                let head = String::from_utf8_lossy(&buf[..headers_end]).to_string();
+                let length: usize = head
+                    .lines()
+                    .find_map(|line| {
+                        line.to_ascii_lowercase()
+                            .strip_prefix("content-length:")
+                            .and_then(|v| v.trim().parse().ok())
+                    })
+                    .unwrap_or(0);
+                let body_start = headers_end + 4;
+                while buf.len() < body_start + length {
+                    let n = socket.read(&mut chunk).await.ok()?;
+                    if n == 0 {
+                        break;
+                    }
+                    buf.extend_from_slice(&chunk[..n]);
+                }
+                let method = head
+                    .lines()
+                    .next()
+                    // `POST /bot<token>/<method>`
+                    .and_then(|line| line.split(' ').nth(1))
+                    .and_then(|path| path.rsplit('/').next())
+                    .unwrap_or_default()
+                    .to_string();
+                let body = parse_body(&buf[body_start..], &head);
+                return Some((method, body));
+            }
+        }
+
+        /// The request body as JSON: either the JSON body itself, or a
+        /// multipart form flattened into an object (each part's value parsed as
+        /// JSON when it is one, so `media` comes back as its array).
+        fn parse_body(body: &[u8], head: &str) -> serde_json::Value {
+            let content_type = head
+                .lines()
+                .find(|line| line.to_ascii_lowercase().starts_with("content-type:"))
+                .unwrap_or_default()
+                .to_ascii_lowercase();
+            let Some(boundary) = content_type
+                .split("boundary=")
+                .nth(1)
+                .map(|b| b.trim().trim_matches('"').to_string())
+            else {
+                return serde_json::from_slice(body).unwrap_or_default();
+            };
+            let text = String::from_utf8_lossy(body);
+            let mut fields = serde_json::Map::new();
+            for part in text.split(&format!("--{boundary}")).skip(1) {
+                let Some((part_head, value)) = part.split_once("\r\n\r\n") else {
+                    continue;
+                };
+                let Some(name) = part_head
+                    .split("name=\"")
+                    .nth(1)
+                    .and_then(|rest| rest.split('"').next())
+                else {
+                    continue;
+                };
+                let value = value.trim_end_matches("\r\n");
+                fields.insert(
+                    name.to_string(),
+                    serde_json::from_str(value).unwrap_or_else(|_| value.into()),
+                );
+            }
+            serde_json::Value::Object(fields)
+        }
+
+        fn find(haystack: &[u8], needle: &[u8]) -> Option<usize> {
+            haystack
+                .windows(needle.len())
+                .position(|window| window == needle)
+        }
+    }
+
    /// Replays a script and records what was sent, so tests can assert the
    /// user-visible text a path produced.
    pub(crate) struct MockSender {
@@ -91,6 +91,15 @@ impl TokenBucket {
        tokio::time::sleep(Duration::from_secs_f64(wait)).await;
    }

+    /// Current balance, for the tests that assert a call site charged the
+    /// bucket (a charge is otherwise only observable as a delay).
+    #[cfg(test)]
+    pub(crate) fn tokens(&self) -> f64 {
+        let mut state = self.state.lock();
+        self.refill(&mut state);
+        state.tokens
+    }
+
    /// True when the bucket has refilled to capacity: no debt outstanding, so
    /// the chat has not sent anything recently.
    fn is_idle(&self) -> bool {
@@ -1396,6 +1396,50 @@ mod tests {
        assert_eq!(sender.calls(), vec!["send_animation", "send_animation"]);
    }

+    /// A media group through a **real** `Bot` — its request building, the
+    /// per-chat limiter, the bot-wide budget — against a stand-in API. The
+    /// scripted mock bypasses `media_sender`'s implementation entirely, so a
+    /// call site that stops charging the limiters (or a broken request shape)
+    /// is invisible to every other test.
+    #[tokio::test]
+    async fn a_media_group_reaches_the_api_through_a_real_bot() {
+        use crate::media_sender::test_support::fake_api::FakeApi;
+        use teloxide::Bot;
+
+        let api = FakeApi::start().await;
+        let bot = Bot::new("42:TEST").set_api_url(api.url());
+        let stores = TestStores::new();
+        let ctx = stores.ctx(&bot);
+        // A chat of its own: the limiter buckets are process-wide.
+        let mut task = sequence_task("https://cdn.example/1.jpg");
+        if let Task::SendMediaSequence { chat_id, .. } = &mut task {
+            *chat_id = 987_654;
+        }
+        let bucket = crate::rate_limit::limiter_for(987_654);
+        let before = bucket.tokens();
+
+        let outcome = send_media_sequence(&ctx, &task).await;
+        eprintln!(
+            "SCRATCH send methods={:?} outcome={outcome:?}",
+            api.methods()
+        );
+        assert!(outcome.is_ok());
+
+        // The request teloxide built: one group, the URL, the caption on the
+        // first item.
+        assert_eq!(api.methods(), vec!["SendMediaGroup"]);
+        let body = api.body("SendMediaGroup");
+        assert_eq!(body["chat_id"], 987_654);
+        assert_eq!(body["media"][0]["media"], "https://cdn.example/1.jpg");
+        assert_eq!(body["media"][0]["caption"], "cap");
+        // …and the send charged the pace limiter before it went out.
+        let after = bucket.tokens();
+        assert!(
+            after < before,
+            "a send must charge the chat's budget ({before} -> {after})"
+        );
+    }
+
    #[tokio::test]
    async fn forward_classifies_retry_after_and_permanent() {
        use teloxide::types::Seconds;