refactor(site): carry site_id on Fetched; unify cache-key site lookup

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

@@ -299,6 +299,7 @@ impl From<Post> for Fetched {
             title: post.text.clone(),
             media: post.media,
             sensitive: post.sensitive,
+            site_id: "bsky",
             render_data,
             _keep_alive: None,
         }

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

@@ -30,6 +30,10 @@ pub struct Fetched {
     pub media: Vec<crate::media::Media>,
     /// Spoiler flag for all media of this post.
     pub sensitive: bool,
+    /// Site id (`"twitter"` / `"bsky"` / `"pixiv"`): the single source of
+    /// truth for site identity — caption-format lookup, cache-key prefix and
+    /// the SetFormat whitelist all derive from it. Set by the producing site.
+    pub site_id: &'static str,
     /// Raw values (pre-escaped) for user-customizable caption formats.
     pub(crate) render_data: Option<RenderData>,
     /// Keeps temp files (e.g. an encoded ugoira MP4) alive until the caller
@@ -50,16 +54,10 @@ pub(crate) struct RenderData {
 
 impl Fetched {
     /// The site this post came from (used for per-site format overrides).
+    /// A thin alias over [`Fetched::site_id`] kept for callers that read the
+    /// site off a fetched post.
     pub fn site_name(&self) -> &'static str {
-        if self.source_url.contains("x.com") || self.source_url.contains("twitter.com") {
+        self.site_id
-            "twitter"
-        } else if self.source_url.contains("bsky.app") {
-            "bsky"
-        } else if self.source_url.contains("pixiv.net") {
-            "pixiv"
-        } else {
-            "unknown"
-        }
     }
 
     /// Renders a user-supplied caption format. The format string is
@@ -177,6 +175,25 @@ pub fn cache_key(url: &str) -> Option<String> {
     None
 }
 
+/// The site id carried by a cache key (`"twitter:123"` → `"twitter"`).
+/// Unknown prefixes fall back to `"unknown"`. The bot uses this on the
+/// link-cache hit path, where no [`Fetched`] is available — the same value
+/// a fresh fetch would read from [`Fetched::site_id`].
+pub fn site_id_from_key(key: &str) -> &'static str {
+    match key.split(':').next() {
+        Some("twitter") => "twitter",
+        Some("pixiv") => "pixiv",
+        Some("bsky") => "bsky",
+        _ => "unknown",
+    }
+}
+
+/// Every supported site id, in dispatch order. The bot's SetFormat whitelist
+/// and per-site caption-format lookup derive from this list.
+pub fn site_ids() -> Vec<&'static str> {
+    vec!["twitter", "bsky", "pixiv"]
+}
+
 #[derive(Debug)]
 pub enum FetchError {
     Http(reqwest::Error),
@@ -476,6 +493,15 @@ mod tests {
         assert_eq!(cache_key("https://example.com/not-a-post"), None);
     }
 
+    #[test]
+    fn site_id_from_key_parses_prefix() {
+        assert_eq!(site_id_from_key("twitter:123"), "twitter");
+        assert_eq!(site_id_from_key("pixiv:123"), "pixiv");
+        assert_eq!(site_id_from_key("bsky:handle.example/3lorem"), "bsky");
+        assert_eq!(site_id_from_key("unknown:1"), "unknown");
+        assert_eq!(site_id_from_key("no-colon"), "unknown");
+    }
+
     #[test]
     fn fetch_error_retryability_classification() {
         // Transient: network errors, explicit transient, pixiv 429/5xx.

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

@@ -142,6 +142,7 @@ impl From<Illustration> for Fetched {
             title: illustration.title.clone(),
             media: illustration.media,
             sensitive: illustration.nsfw,
+            site_id: "pixiv",
             render_data,
             _keep_alive: illustration._keep_alive,
         }

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

@@ -60,6 +60,7 @@ fn empty_fetched(url: &str) -> Fetched {
         title: String::new(),
         media: vec![],
         sensitive: true,
+        site_id: "twitter",
         render_data: None,
         _keep_alive: None,
     }
@@ -301,6 +302,7 @@ impl From<Tweet> for Fetched {
             title: tweet.text.clone(),
             media: tweet.media,
             sensitive: tweet.sensitive,
+            site_id: "twitter",
             render_data,
             _keep_alive: None,
         }

crates/xmedia-bot/src/handlers.rs

@@ -402,7 +402,7 @@ async fn execute_command(
                     return Ok(());
                 }
             };
-            if !["twitter", "bsky", "pixiv"].contains(&site) {
+            if !x_media::site::site_ids().contains(&site) {
                 reply(
                     bot.clone(),
                     message.clone(),
@@ -636,7 +636,9 @@ async fn url_media(bot: Bot, message: &Message, url: &str) {
     {
         log::debug!("link cache hit for {key}");
         let chat_data = CHAT_STORE.get(chat_id).await;
-        let site = key.split(':').next().unwrap_or("unknown");
+        // Cache keys are prefixed with the site id ("twitter:…"), matching
+        // the value a fresh fetch would read from Fetched::site_id.
+        let site = x_media::site::site_id_from_key(&key);
         let format = chat_data
             .message_format
             .get(site)