bump version to 1.0.5

AGENTS.md

@@ -27,7 +27,7 @@ The `x-media` library: `site::fetch(url)` dispatches (in order) twitter → bsky
 | Path | Purpose |
 |---|---|
 | `crates/x-media/src/` | Fetch library. `site/mod.rs` = dispatcher + `Fetched`/`FetchError`/`download_media`/`media_size`; `media.rs` = `Media` enum; `examples/fetch.rs` = end-to-end usage sample |
-| `crates/x-media/src/site/<twitter\|pixiv\|bsky>/` | One directory per site: `mod.rs` (re-exports), `interface.rs` (PATTERN, `enabled()`, `fetch_from_url()`, site struct, `From<SiteStruct> for Fetched`), `model.rs` (serde DTOs). Pixiv adds `api.rs` (auth + transport) |
+| `crates/x-media/src/site/<twitter\|pixiv\|bsky>/` | One directory per site: `mod.rs` (re-exports), `interface.rs` (PATTERN, `enabled()`, `fetch_from_url()`, site struct, `From<SiteStruct> for Fetched`), `model.rs` (serde DTOs). Pixiv adds `api.rs` (auth + transport); twitter adds `auth.rs` (logged-in GraphQL `TweetDetail` fallback for NSFW tweets, gated on `TWITTER_AUTH_TOKEN`) |
 | `crates/xmedia-bot/src/main.rs` | Entry point: env/log init, queue worker start, pixiv validation, 300 s edit-expiry sweep, dptree handler tree, webhook vs polling dispatch |
 | `crates/xmedia-bot/src/config.rs` | Manual env parsing into `Config` |
 | `crates/xmedia-bot/src/handlers.rs` | `Command` enum (teloxide `BotCommands`), message/inline/callback handlers, URL extraction, global statics |
@@ -72,7 +72,7 @@ Docker: `docker build -t tgxmb .` then `docker run --rm -d --name tgxmb --env-fi
 | `crates/x-media/src/site/pixiv/api.rs` | OAuth token exchange (hardcoded app client id/secret), access-token cache, ugoira zip→MP4 via ffmpeg in `spawn_blocking` |
 | `Dockerfile` | Multi-stage: cached dep layer via stub sources + `touch *.rs` mtime hack, static ffmpeg from ffmpeg.martin-riedl.de (`FFMPEG_URL` arg, `unzip -t` integrity check), `debian:bookworm-slim` runtime, entrypoint |
 | `docker-entrypoint.sh` | Privilege drop: `useradd` with `LOCAL_USER_ID` (default 9001) + `setpriv` (no gosu on bookworm-slim) |
-| `docker-compose.yml.example` | Deployment env reference (real `docker-compose.yml` is gitignored). Ships nginx-proxy + acme-companion: webhook mode needs TLS termination in front (teloxide's axum listener is HTTP-only; `WEBHOOK_CERT` only feeds `set_webhook`), bot exposes `VIRTUAL_HOST`/`VIRTUAL_PORT` on the shared `proxy` network, no host port |
+| `docker-compose.yml.example` | Deployment env reference (real `docker-compose.yml` is gitignored). Ships nginx-proxy + acme-companion: webhook mode needs TLS termination in front (teloxide's axum listener is HTTP-only; `WEBHOOK_CERT` only feeds `set_webhook`), bot exposes `VIRTUAL_HOST`/`VIRTUAL_PORT` on the shared `proxy` network, no host port; container names `nginx-proxy`/`acme-companion`/`tgxmb`, start order via `depends_on` (proxy → acme → bot) |
 | `.github/workflows/docker.yml` | CI: build+push to Docker Hub on tag `v*`/master; **no test step**; buildx gha cache (`cache-from`/`cache-to`, scope `tgxmb-build`, `mode=max`) so cargo deps + ffmpeg layers are restored across runs |
 | `README.md` | Feature docs + command table (Chinese) |
 
@@ -81,7 +81,7 @@ Docker: `docker build -t tgxmb .` then `docker run --rm -d --name tgxmb --env-fi
 - **Rust, stable, edition 2024**, workspace resolver 3. No `rust-version`/MSRV pin, no `rust-toolchain.toml` — recent stable is assumed. No nightly features.
 - Package manager: **Cargo** (workspace with path dep `x-media` ← `xmedia-bot`). No `[workspace.package]`/shared deps — each crate lists deps independently.
 - **Two reqwest versions coexist in the lock** (0.12.28 via teloxide, 0.13.3 in x-media) — don't unify casually.
-- Config is **environment-variable driven** (dotenv loads `.env`, gitignored; no `.env.example` exists). Key vars: `TELOXIDE_TOKEN` (required), `PIXIV_REFRESH_TOKEN`, `BOT_ADMIN` (comma-separated ids), `EDIT_MESSAGE_TTL_SECONDS` (default 86400), `WEBHOOK`/`WEBHOOK_URL`/`WEBHOOK_LISTEN`/`WEBHOOK_PORT`/`WEBHOOK_CERT`/`WEBHOOK_SECRET_TOKEN` (webhook mode requires URL/listen/port, `.expect`ed; `WEBHOOK_CERT` is Telegram-facing self-signed validation only — TLS must be terminated by a reverse proxy), `RUST_LOG`, `TELOXIDE_PROXY`, `LOCAL_USER_ID` (entrypoint only).
+- Config is **environment-variable driven** (dotenv loads `.env`, gitignored; no `.env.example` exists). Key vars: `TELOXIDE_TOKEN` (required), `PIXIV_REFRESH_TOKEN`, `TWITTER_AUTH_TOKEN` (optional; x.com `auth_token` cookie — enables the logged-in GraphQL fallback that fetches NSFW tweets syndication withholds), `BOT_ADMIN` (comma-separated ids), `EDIT_MESSAGE_TTL_SECONDS` (default 86400), `WEBHOOK`/`WEBHOOK_URL`/`WEBHOOK_LISTEN`/`WEBHOOK_PORT`/`WEBHOOK_CERT`/`WEBHOOK_SECRET_TOKEN` (webhook mode requires URL/listen/port, `.expect`ed; `WEBHOOK_CERT` is Telegram-facing self-signed validation only — TLS must be terminated by a reverse proxy), `RUST_LOG`, `TELOXIDE_PROXY`, `LOCAL_USER_ID` (entrypoint only).
 - SQLite via `rusqlite` with `bundled` feature (no system libsqlite needed). DB file `data/task_queue.db` is CWD-relative — run from the workspace root, or `/app` in Docker. Mount `./data` and `./cert` volumes.
 - `.gitattributes` enforces LF for `*.sh` (CRLF breaks shebangs in containers). `.gitignore`: `.env`, `data/`, `cert/`, `docker-compose.yml`, `/target`, `.idea/`.
 - Docs are in Chinese; user-facing bot strings too. Keep that convention when editing captions/templates/docs.

Cargo.lock

@@ -3296,12 +3296,13 @@ checksum = "1ffae5123b2d3fc086436f8834ae3ab053a283cfac8fe0a0b8eaae044768a4c4"
 
 [[package]]
 name = "x-media"
-version = "1.0.4"
+version = "1.0.5"
 dependencies = [
  "bytes",
  "dotenv",
  "html-escape",
  "log",
+ "rand 0.8.6",
  "regex",
  "reqwest 0.13.3",
  "serde",
@@ -3314,7 +3315,7 @@ dependencies = [
 
 [[package]]
 name = "xmedia-bot"
-version = "1.0.4"
+version = "1.0.5"
 dependencies = [
  "dotenv",
  "html-escape",

README.md

@@ -28,7 +28,9 @@ docker build -t tgxmb .
 docker run --rm -d --name tgxmb --env-file .env -v ./data:/app/data tgxmb
 ```
 
-环境变量：`TELOXIDE_TOKEN`（必填）、`PIXIV_REFRESH_TOKEN`、`BOT_ADMIN`、`EDIT_MESSAGE_TTL_SECONDS`、`RUST_LOG`、`WEBHOOK*`。
+环境变量：`TELOXIDE_TOKEN`（必填）、`PIXIV_REFRESH_TOKEN`、`BOT_ADMIN`、`EDIT_MESSAGE_TTL_SECONDS`、`RUST_LOG`、`WEBHOOK*`、`TWITTER_AUTH_TOKEN`（可选）。
+
+NSFW 推文：公开的 syndication 接口不返回敏感内容。设置 `TWITTER_AUTH_TOKEN`（登录 x.com 后浏览器 Cookie 里的 `auth_token` 值）后，bot 会仅在遇到 NSFW 推文时以登录态获取媒体；未设置则提示无媒体。
 
 ### Webhook 部署（需要反向代理）
 

crates/x-media/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "x-media"
-version = "1.0.4"
+version = "1.0.5"
 edition = "2024"
 
 [dependencies]
@@ -13,6 +13,7 @@ url = "2.5.2"
 bytes = "1"
 zip = "2"
 tempfile = "3"
+rand = "0.8"
 log = "0.4"
 tokio = { version = "1.40", features = ["time"] }
 

crates/x-media/src/site/mod.rs

@@ -89,6 +89,9 @@ pub enum FetchError {
     Pixiv(PixivError),
     NotFound,
     Blocked,
+    /// The post exists but its content is withheld (twitter NSFW /
+    /// age-restricted tweets come back as an empty `{}` from syndication).
+    Sensitive,
 }
 
 impl fmt::Display for FetchError {
@@ -99,6 +102,7 @@ impl fmt::Display for FetchError {
             FetchError::Pixiv(e) => write!(f, "pixiv error: {e}"),
             FetchError::NotFound => write!(f, "not found"),
             FetchError::Blocked => write!(f, "blocked"),
+            FetchError::Sensitive => write!(f, "content withheld (sensitive)"),
         }
     }
 }
@@ -109,7 +113,7 @@ impl std::error::Error for FetchError {
             FetchError::Http(e) => Some(e),
             FetchError::Json(e) => Some(e),
             FetchError::Pixiv(e) => Some(e),
-            FetchError::NotFound | FetchError::Blocked => None,
+            FetchError::NotFound | FetchError::Blocked | FetchError::Sensitive => None,
         }
     }
 }

crates/x-media/src/site/twitter/auth.rs

@@ -0,0 +1,376 @@
+//! Authenticated fallback for tweets the public syndication endpoint refuses
+//! to serve (NSFW / age-restricted tweets come back as an empty `{}`).
+//!
+//! Mirrors nazurin's web API client ([`web.py`]) and is used *only* when
+//! syndication reports [`FetchError::Sensitive`]: the private GraphQL
+//! `TweetDetail` endpoint, authenticated with a browser session cookie from
+//! `TWITTER_AUTH_TOKEN` (the `auth_token` cookie value of a logged-in x.com
+//! session). A fresh random `ct0` is generated per call; X checks that the
+//! `x-csrf-token` header matches the cookie, not that it issued the value.
+//!
+//! [`web.py`]: https://github.com/y-young/nazurin/blob/master/nazurin/sites/twitter/api/web.py
+//!
+//! # Caveats
+//! - X rotates the GraphQL query id when it rolls the web app; if requests
+//!   start failing, update [`TWEET_DETAIL_QUERY_ID`]. Fresh references from
+//!   the actively maintained FxEmbed/FxEmbed: TweetDetail
+//!   `R9IzzyzQBV87-DOWpcvDmw`, TweetResultByRestId `f2sagi1jweVHFkTUIHzmMQ`
+//!   (the latter is anonymous and surfaces NSFW tweets as
+//!   `reason: NsfwLoggedOut`).
+//! - `x-client-transaction-id` is only required for `SearchTimeline`
+//!   (verified against FxEmbed's `proxy/allowlist.ts`) — TweetDetail works
+//!   without it; no need for the nazurin home-page/JS-bundle derivation.
+
+use std::sync::LazyLock;
+
+use serde_json::{json, Value};
+
+use crate::site::FetchError;
+
+use super::interface::Tweet;
+
+/// `auth_token` cookie of a logged-in x.com session; enables the fallback.
+/// Trimmed: a CRLF `.env` (Windows) leaves a trailing `\r` on the value,
+/// which would make the Cookie header invalid.
+static AUTH_TOKEN: LazyLock<Option<String>> = LazyLock::new(|| {
+    std::env::var("TWITTER_AUTH_TOKEN")
+        .ok()
+        .map(|s| s.trim().to_string())
+        .filter(|s| !s.is_empty())
+});
+
+/// Public "logged in" client token used by the x.com web app.
+const LOGGED_IN_BEARER: &str =
+    "Bearer AAAAAAAAAAAAAAAAAAAAANRILgAAAAAAnNwIzUejRCOuH5E6I8xnZz4puTs%3D1Zv7ttfk8LF81IUq16cHjhLTvJu4FA33AGWWjCpTnA";
+
+/// `TweetDetail` query id (from nazurin; still valid as of 2026-08,
+/// corroborated by the current FxEmbed build — see module caveats).
+const TWEET_DETAIL_QUERY_ID: &str = "_8aYOgEDz35BrBcBal1-_w";
+
+fn variables(id: &str) -> Value {
+    json!({
+        "focalTweetId": id,
+        "with_rux_injections": false,
+        "includePromotedContent": false,
+        "withCommunity": true,
+        "withQuickPromoteEligibilityTweetFields": false,
+        "withBirdwatchNotes": false,
+        "withVoice": true,
+    })
+}
+
+fn features() -> Value {
+    json!({
+        "rweb_video_screen_enabled": false,
+        "profile_label_improvements_pcf_label_in_post_enabled": true,
+        "rweb_tipjar_consumption_enabled": true,
+        "verified_phone_label_enabled": false,
+        "creator_subscriptions_tweet_preview_api_enabled": true,
+        "responsive_web_graphql_timeline_navigation_enabled": true,
+        "responsive_web_graphql_skip_user_profile_image_extensions_enabled": false,
+        "premium_content_api_read_enabled": false,
+        "communities_web_enable_tweet_community_results_fetch": true,
+        "c9s_tweet_anatomy_moderator_badge_enabled": true,
+        "responsive_web_grok_analyze_button_fetch_trends_enabled": false,
+        "responsive_web_grok_analyze_post_followups_enabled": true,
+        "responsive_web_jetfuel_frame": false,
+        "responsive_web_grok_share_attachment_enabled": true,
+        "articles_preview_enabled": true,
+        "responsive_web_edit_tweet_api_enabled": true,
+        "graphql_is_translatable_rweb_tweet_is_translatable_enabled": true,
+        "view_counts_everywhere_api_enabled": true,
+        "longform_notetweets_consumption_enabled": true,
+        "responsive_web_twitter_article_tweet_consumption_enabled": true,
+        "tweet_awards_web_tipping_enabled": false,
+        "responsive_web_grok_show_grok_translated_post": false,
+        "responsive_web_grok_analysis_button_from_backend": true,
+        "creator_subscriptions_quote_tweet_preview_enabled": false,
+        "freedom_of_speech_not_reach_fetch_enabled": true,
+        "standardized_nudges_misinfo": true,
+        "tweet_with_visibility_results_prefer_gql_limited_actions_policy_enabled": true,
+        "longform_notetweets_rich_text_read_enabled": true,
+        "longform_notetweets_inline_media_enabled": true,
+        "responsive_web_grok_image_annotation_enabled": true,
+        "responsive_web_enhance_cards_enabled": false,
+    })
+}
+
+/// Whether the authenticated fallback is available.
+pub fn enabled() -> bool {
+    AUTH_TOKEN.is_some()
+}
+
+/// Fetches a tweet as the logged-in user via the private GraphQL API.
+/// Returns the syndication-shaped [`Tweet`] (media included for NSFW posts).
+pub async fn fetch(id: &str) -> Result<Tweet, FetchError> {
+    let token = AUTH_TOKEN
+        .as_deref()
+        .ok_or(FetchError::Sensitive)?;
+    // 16 random bytes as 32 hex chars: X rejects ct0 values of any other
+    // length with 403 code 353 ("matching csrf cookie and header").
+    let ct0: String = (0..16)
+        .map(|_| format!("{:02x}", rand::random::<u8>()))
+        .collect();
+
+    let response = crate::site::CLIENT
+        .get(format!(
+            "https://x.com/i/api/graphql/{TWEET_DETAIL_QUERY_ID}/TweetDetail"
+        ))
+        .query(&[
+            ("variables", variables(id).to_string()),
+            ("features", features().to_string()),
+        ])
+        .header("authorization", LOGGED_IN_BEARER)
+        .header("x-csrf-token", &ct0)
+        .header("x-twitter-auth-type", "OAuth2Session")
+        .header("cookie", format!("auth_token={token}; ct0={ct0}"))
+        .header("x-twitter-client-language", "en")
+        .header("x-twitter-active-user", "yes")
+        .header("referer", "https://x.com/")
+        .send()
+        .await?;
+    if !response.status().is_success() {
+        log::warn!("twitter auth fetch {id}: HTTP {}", response.status());
+        return Err(FetchError::NotFound);
+    }
+    let text = response.text().await?;
+    let json: Value = serde_json::from_str(&text)?;
+    let result = parse_tweet_result(&json, id)?;
+    let syndication_shape = to_syndication_shape(&result)
+        .ok_or_else(|| FetchError::Json(serde_json::Error::io(std::io::Error::new(
+            std::io::ErrorKind::InvalidData,
+            "missing tweet fields in GraphQL response",
+        ))))?;
+    Tweet::from_syndication_json(&syndication_shape.to_string()).map_err(FetchError::Json)
+}
+
+/// Locates the tweet for `id` in a `TweetDetail` response and unwraps
+/// visibility wrappers / retweets, mirroring nazurin's `_process_response`.
+fn parse_tweet_result(json: &Value, id: &str) -> Result<Value, FetchError> {
+    if let Some(errors) = json.get("errors").and_then(|e| e.as_array()) {
+        let messages: Vec<&str> = errors
+            .iter()
+            .filter_map(|e| e.get("message").and_then(|m| m.as_str()))
+            .collect();
+        log::warn!("twitter auth fetch {id} failed: {}", messages.join("; "));
+        return Err(FetchError::NotFound);
+    }
+
+    let instructions = json
+        .pointer("/data/threaded_conversation_with_injections_v2/instructions")
+        .and_then(|v| v.as_array())
+        .ok_or(FetchError::NotFound)?;
+    for instruction in instructions {
+        if instruction.get("type").and_then(|t| t.as_str()) != Some("TimelineAddEntries") {
+            continue;
+        }
+        let entries = instruction
+            .get("entries")
+            .and_then(|e| e.as_array())
+            .ok_or(FetchError::NotFound)?;
+        let wanted = format!("tweet-{id}");
+        for entry in entries {
+            if entry.get("entryId").and_then(|i| i.as_str()) == Some(wanted.as_str()) {
+                let result = entry
+                    .pointer("/content/itemContent/tweet_results/result")
+                    .ok_or(FetchError::NotFound)?;
+                return normalize_tweet_result(result);
+            }
+        }
+    }
+    Err(FetchError::NotFound)
+}
+
+/// Unwraps TweetTombstone/TweetUnavailable errors, the
+/// TweetWithVisibilityResults wrapper and retweets, returning the
+/// `{core, legacy, ...}` tweet object.
+fn normalize_tweet_result(result: &Value) -> Result<Value, FetchError> {
+    match result.get("__typename").and_then(|t| t.as_str()) {
+        Some("TweetTombstone") => {
+            let text = result
+                .pointer("/tombstone/text/text")
+                .and_then(|t| t.as_str())
+                .unwrap_or("tweet is unavailable");
+            log::warn!("twitter auth fetch: tombstone: {text}");
+            return Err(FetchError::NotFound);
+        }
+        Some("TweetUnavailable") => {
+            let reason = result
+                .get("reason")
+                .and_then(|r| r.as_str())
+                .unwrap_or("unknown");
+            log::warn!("twitter auth fetch: tweet unavailable: {reason}");
+            return Err(FetchError::NotFound);
+        }
+        _ => {}
+    }
+
+    // TweetWithVisibilityResults (e.g. limited replies) nests the real tweet.
+    let tweet = result.get("tweet").unwrap_or(result);
+    // A retweet's media lives on the original tweet.
+    if let Some(original) = tweet.pointer("/legacy/retweeted_status_result/result") {
+        return Ok(original.clone());
+    }
+    Ok(tweet.clone())
+}
+
+/// Maps a GraphQL `{core, legacy, ...}` tweet onto the syndication JSON
+/// shape [`Tweet::from_syndication_json`] parses, so the existing text /
+/// media handling (t.co expansion, `name=orig`, mp4 variant) is reused.
+fn to_syndication_shape(tweet: &Value) -> Option<Value> {
+    let legacy = tweet.get("legacy")?;
+    let user = tweet.pointer("/core/user_results/result/legacy")?;
+    Some(json!({
+        "id_str": legacy.get("id_str"),
+        "text": legacy.get("full_text"),
+        "user": {
+            "name": user.get("name"),
+            "screen_name": user.get("screen_name"),
+        },
+        "possibly_sensitive": legacy.get("possibly_sensitive"),
+        "display_text_range": legacy.get("display_text_range"),
+        "entities": legacy.get("entities"),
+        "mediaDetails": legacy.pointer("/extended_entities/media"),
+    }))
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn tweet_result() -> Value {
+        json!({
+            "__typename": "Tweet",
+            "core": {
+                "user_results": {
+                    "result": {
+                        "legacy": { "name": "Display Name", "screen_name": "nsfw_author" }
+                    }
+                }
+            },
+            "legacy": {
+                "id_str": "2083868672721039569",
+                "full_text": "nsfw content https://t.co/abc123",
+                "display_text_range": [0, 12],
+                "possibly_sensitive": true,
+                "entities": {
+                    "urls": [
+                        { "url": "https://t.co/abc123", "expanded_url": "https://example.com/x" }
+                    ]
+                },
+                "extended_entities": {
+                    "media": [
+                        {
+                            "type": "photo",
+                            "media_url_https": "https://pbs.twimg.com/media/nsfw.jpg",
+                            "original_info": { "width": 1200, "height": 800 }
+                        },
+                        {
+                            "type": "video",
+                            "media_url_https": "https://pbs.twimg.com/thumb.jpg",
+                            "video_info": {
+                                "variants": [
+                                    { "content_type": "application/x-mpegURL", "url": "https://x.com/pl.m3u8" },
+                                    { "content_type": "video/mp4", "url": "https://video.twimg.com/nsfw.mp4" }
+                                ]
+                            }
+                        }
+                    ]
+                }
+            }
+        })
+    }
+
+    fn conversation(tweet: Value) -> Value {
+        json!({
+            "data": {
+                "threaded_conversation_with_injections_v2": {
+                    "instructions": [
+                        { "type": "TimelineAddEntries", "entries": [
+                            { "entryId": "tweet-2083868672721039569",
+                              "content": { "itemContent": { "tweet_results": { "result": tweet } } } }
+                        ]}
+                    ]
+                }
+            }
+        })
+    }
+
+    #[test]
+    fn parses_graphql_tweet_into_fetched() {
+        let json = conversation(tweet_result());
+        let result = parse_tweet_result(&json, "2083868672721039569").unwrap();
+        let shape = to_syndication_shape(&result).unwrap();
+        let tweet = Tweet::from_syndication_json(&shape.to_string()).unwrap();
+        let fetched: crate::site::Fetched = tweet.into();
+
+        assert!(fetched.sensitive);
+        assert_eq!(fetched.media.len(), 2);
+        match &fetched.media[0] {
+            crate::media::Media::Illustration { url, .. } => {
+                assert_eq!(url, "https://pbs.twimg.com/media/nsfw.jpg?name=orig");
+            }
+            other => panic!("expected illustration, got {other:?}"),
+        }
+        match &fetched.media[1] {
+            crate::media::Media::Video { url, .. } => {
+                assert_eq!(url, "https://video.twimg.com/nsfw.mp4");
+            }
+            other => panic!("expected video, got {other:?}"),
+        }
+        assert_eq!(fetched.source_url, "https://x.com/nsfw_author/status/2083868672721039569");
+        // display_text_range cuts the trailing t.co link.
+        assert_eq!(fetched.title, "nsfw content");
+    }
+
+    #[test]
+    fn unwraps_retweet_to_original() {
+        let original = tweet_result();
+        let mut rt = tweet_result();
+        rt["legacy"]["retweeted_status_result"] = json!({ "result": original });
+        let json = conversation(rt);
+        let result = parse_tweet_result(&json, "2083868672721039569").unwrap();
+        assert!(result.pointer("/legacy/retweeted_status_result").is_none());
+        assert_eq!(result.pointer("/legacy/id_str").unwrap(), "2083868672721039569");
+    }
+
+    #[test]
+    fn error_response_maps_to_not_found() {
+        let json = json!({ "errors": [{ "message": "NsfwLoggedOut" }] });
+        assert!(matches!(
+            parse_tweet_result(&json, "1"),
+            Err(FetchError::NotFound)
+        ));
+    }
+
+    #[test]
+    fn missing_entry_maps_to_not_found() {
+        let json = conversation(json!({ "__typename": "Tweet" }));
+        assert!(matches!(
+            parse_tweet_result(&json, "999"),
+            Err(FetchError::NotFound)
+        ));
+    }
+
+    #[test]
+    fn tombstone_maps_to_not_found() {
+        let tombstone = json!({
+            "__typename": "TweetTombstone",
+            "tombstone": { "text": { "text": "Age-restricted adult content" } }
+        });
+        let json = conversation(tombstone);
+        assert!(matches!(
+            parse_tweet_result(&json, "2083868672721039569"),
+            Err(FetchError::NotFound)
+        ));
+    }
+
+    #[test]
+    fn visibility_wrapper_unwraps() {
+        let inner = tweet_result();
+        let wrapped = json!({ "__typename": "TweetWithVisibilityResults", "tweet": inner });
+        let json = conversation(wrapped);
+        let result = parse_tweet_result(&json, "2083868672721039569").unwrap();
+        assert_eq!(result.get("__typename").unwrap(), "Tweet");
+    }
+}

crates/x-media/src/site/twitter/interface.rs

@@ -19,7 +19,44 @@ pub async fn fetch_from_url(url: &str) -> Result<Fetched, FetchError> {
         .and_then(|caps| caps.get(1))
         .map(|m| m.as_str())
         .ok_or(FetchError::NotFound)?;
-    Ok(fetch(id).await?.into())
+    match fetch(id).await {
+        Ok(tweet) => Ok(tweet.into()),
+        // Syndication withholds NSFW/age-restricted tweets (empty `{}`).
+        // Retry as the logged-in user when TWITTER_AUTH_TOKEN is set;
+        // otherwise degrade to an empty result (the bot replies
+        // "No media found").
+        Err(FetchError::Sensitive) => {
+            if super::auth::enabled() {
+                match super::auth::fetch(id).await {
+                    Ok(tweet) => Ok(tweet.into()),
+                    Err(e) => {
+                        log::warn!("twitter auth fallback failed for {id}: {e}");
+                        Ok(empty_fetched(url))
+                    }
+                }
+            } else {
+                log::info!(
+                    "tweet {id} is sensitive; set TWITTER_AUTH_TOKEN to fetch NSFW media"
+                );
+                Ok(empty_fetched(url))
+            }
+        }
+        Err(e) => Err(e),
+    }
+}
+
+/// A Fetched with no media for withheld tweets: the bot replies
+/// "No media found" and moves on instead of erroring.
+fn empty_fetched(url: &str) -> Fetched {
+    Fetched {
+        source_url: url.to_string(),
+        caption: url.to_string(),
+        title: String::new(),
+        media: vec![],
+        sensitive: true,
+        render_data: None,
+        _keep_alive: None,
+    }
 }
 
 /// Fetches a tweet from the syndication endpoint. Deleted/blocked tweets
@@ -44,6 +81,15 @@ pub async fn fetch(id: &str) -> Result<Tweet, FetchError> {
     {
         return Err(FetchError::NotFound);
     }
+    // NSFW / age-restricted tweets exist but are served as an empty `{}` —
+    // they surface as FetchError::Sensitive so the caller can retry as a
+    // logged-in user.
+    if serde_json::from_str::<serde_json::Value>(&text)
+        .map(|v| v.get("id_str").is_none())
+        .unwrap_or(false)
+    {
+        return Err(FetchError::Sensitive);
+    }
     Ok(Tweet::from_syndication_json(&text).map_err(FetchError::Json)?)
 }
 
@@ -159,21 +205,17 @@ impl Tweet {
 }
 
 /// The raw syndication `text` ends with the appended media short link
-/// (" https://t.co/wmI8McgXul"). `display_text_range` (UTF-16 indices) marks
-/// the visible text; a regex strips any remaining trailing t.co link when the
-/// range is absent or a tweet ends in a URL short link.
+/// (" https://t.co/wmI8McgXul"). `display_text_range` marks the visible text;
+/// a regex strips any remaining trailing t.co link when the range is absent
+/// or a tweet ends in a URL short link.
+///
+/// X reports these indices in Unicode **code points**, not UTF-16 units
+/// (verified against GraphQL responses containing emoji: cutting an emoji
+/// tweet by UTF-16 units silently drops the character after the emoji).
 fn strip_trailing_short_links(text: &str, display_text_range: Option<[usize; 2]>) -> String {
     let mut out = match display_text_range {
         Some([start, end]) if start < end => {
-            let units: Vec<u16> = text
-                .encode_utf16()
-                .skip(start)
-                .take(end - start)
-                .collect();
-            // Drop the replacement char that a surrogate cut at the boundary
-            // would produce (the range end is a valid UTF-16 boundary in
-            // practice, so this is just a safety net).
-            String::from_utf16_lossy(&units).replace('\u{FFFD}', "")
+            text.chars().skip(start).take(end - start).collect()
         }
         _ => text.to_string(),
     };

crates/x-media/src/site/twitter/mod.rs

@@ -1,3 +1,4 @@
+mod auth;
 mod interface;
 mod model;
 

crates/x-media/src/site/twitter/model.rs

@@ -10,7 +10,7 @@ pub struct SyndicationTweet {
     #[serde(default)]
     pub possibly_sensitive: Option<bool>,
     /// Visible-text span; the raw `text` field has the appended media short
-    /// link after it. Indices are UTF-16 code units.
+    /// link after it. Indices are Unicode code points (not UTF-16 units).
     #[serde(default, rename = "display_text_range")]
     pub display_text_range: Option<[usize; 2]>,
     #[serde(default)]

crates/xmedia-bot/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "xmedia-bot"
-version = "1.0.4"
+version = "1.0.5"
 edition = "2024"
 
 [dependencies]

docker-compose.yml.example

@@ -16,6 +16,7 @@ services:
     networks: [proxy]
     labels:
       - 'com.github.jrcs.letsencrypt_nginx_proxy_companion.nginx_proxy=true'
+    container_name: nginx-proxy
 
   acme-companion:
     image: nginxproxy/acme-companion
@@ -29,6 +30,7 @@ services:
       - ./nginx-html:/usr/share/nginx/html:rw
       - ./nginx-acme:/etc/acme.sh
     networks: [proxy]
+    container_name: acme-companion
     depends_on:
       - nginx-proxy
 
@@ -40,6 +42,9 @@ services:
       TELOXIDE_TOKEN: ''
       BOT_ADMIN: ''
       PIXIV_REFRESH_TOKEN: ''
+      # Optional: x.com session cookie (auth_token) — fetches NSFW tweets
+      # that the public syndication endpoint withholds.
+      TWITTER_AUTH_TOKEN: ''
       EDIT_MESSAGE_TTL_SECONDS: '86400'
       RUST_LOG: 'info'
       VIRTUAL_HOST: 'bot.example.com'
@@ -54,6 +59,8 @@ services:
     volumes:
       - ./data:/app/data
     networks: [proxy]
+    depends_on:
+      - nginx-proxy
     container_name: tgxmb
 
 networks: