fix(gl): derive View: URL from node instead of hardcoding gitlawb.com (#370)

.env.example

@@ -10,6 +10,12 @@ GITLAWB_KEY=/data/keys/identity.pem
 # Publicly reachable URL of this node (used in peer announcements)
 GITLAWB_PUBLIC_URL=https://your-node.example.com
 
+# Base URL for the web view of repos on this node (used by `gl` to print a
+# working View: link after repo creation). Omit for nodes with no web front-end.
+# Distinct from GITLAWB_PUBLIC_URL: that is API reachability for peers;
+# this is browser reachability for humans.
+# GITLAWB_WEB_URL=https://gitlawb.com
+
 # ── Server ────────────────────────────────────────────────────────────────
 GITLAWB_HOST=0.0.0.0
 GITLAWB_PORT=7545

Cargo.toml

@@ -51,6 +51,8 @@ tracing-subscriber = { version = "0.3", features = ["env-filter"] }
 chrono = { version = "0.4", features = ["serde"] }
 # uuid
 uuid = { version = "1", features = ["v4"] }
+# URL parsing (absolute browser URLs for GITLAWB_WEB_URL / node web_url)
+url = "2"
 # http client
 reqwest = { version = "0.12", features = ["blocking", "json", "multipart", "rustls-tls"], default-features = false }
 # HMAC

crates/gitlawb-node/Cargo.toml

@@ -23,6 +23,7 @@ tracing = { workspace = true }
 tracing-subscriber = { workspace = true }
 chrono = { workspace = true }
 uuid = { workspace = true }
+url = { workspace = true }
 axum = { version = "0.8", features = ["http1", "http2", "json", "ws"] }
 async-graphql = { version = "7", features = ["chrono", "uuid", "tracing"] }
 async-graphql-axum = "7"

crates/gitlawb-node/src/config.rs

@@ -63,6 +63,12 @@ pub struct Config {
     #[arg(long, env = "GITLAWB_PUBLIC_URL")]
     pub public_url: Option<String>,
 
+    /// Base URL for the web view of repos on this node (e.g. https://gitlawb.com).
+    /// When set, `GET /` advertises it as `web_url` so the CLI can print a
+    /// working `View:` link.  Omit for nodes that have no web front-end.
+    #[arg(long, env = "GITLAWB_WEB_URL")]
+    pub web_url: Option<String>,
+
     /// Comma-separated list of bootstrap peer URLs to announce to on startup
     #[arg(long, env = "GITLAWB_BOOTSTRAP_PEERS", value_delimiter = ',')]
     pub bootstrap_peers: Vec<String>,
@@ -583,10 +589,60 @@ impl Config {
                 floor
             ));
         }
+        // GITLAWB_WEB_URL is advertised in GET / so the CLI can print a working
+        // View: link. Clap maps "" to Some("") which would produce a broken URL;
+        // reject early instead of serving a malformed link. Non-blank values must
+        // additionally parse as an absolute http(s) URL — the CLI appends
+        // `/{owner}/{repo}` to it, so scheme-less hosts ("gitlawb.com") and other
+        // garbage would render links no browser can follow.
+        if let Some(raw) = &self.web_url {
+            match validate_web_url(raw) {
+                Ok(()) => {}
+                Err(reason) => {
+                    return Err(format!(
+                        "GITLAWB_WEB_URL {reason} — \
+                         set it to an absolute URL like https://gitlawb.com or leave it unset."
+                    ));
+                }
+            }
+        }
         Ok(())
     }
 }
 
+/// Validate a `web_url` value for use as a browser-reachable base URL.
+/// Blank values are rejected (clap maps `--web-url ""` to `Some("")`), and
+/// non-blank values must parse as absolute `http`/`https` URLs with no query
+/// or fragment — the CLI treats this as a string prefix to append paths to,
+/// so anything else produces links no browser can follow (`?a=1/owner/repo`
+/// puts the repo path inside the query string).
+pub(crate) fn validate_web_url(raw: &str) -> Result<(), String> {
+    if raw.trim().is_empty() {
+        return Err("must not be empty or whitespace-only".into());
+    }
+    let parsed: url::Url = raw
+        .trim()
+        .parse()
+        .map_err(|_| "is not a valid absolute URL".to_string())?;
+    match parsed.scheme() {
+        "http" | "https" => {}
+        other => return Err(format!("must use http or https, got '{other}:'")),
+    }
+    // url::Url cannot represent a URL without a host for http/https schemes, so
+    // reaching here guarantees an absolute browser-usable base.
+    if parsed.query().is_some() {
+        return Err(
+            "must not contain a query string — it is used as a path prefix for View links".into(),
+        );
+    }
+    if parsed.fragment().is_some() {
+        return Err(
+            "must not contain a fragment — it is used as a path prefix for View links".into(),
+        );
+    }
+    Ok(())
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
@@ -973,4 +1029,76 @@ mod tests {
             "db_max_connections at the floor (pushes + headroom) must validate"
         );
     }
+
+    #[test]
+    fn web_url_rejects_empty_and_whitespace() {
+        // Unset is fine.
+        Config::parse_from(["gitlawb-node"])
+            .validate()
+            .expect("no web_url must validate");
+
+        // A real URL validates.
+        let mut cfg = Config::parse_from(["gitlawb-node"]);
+        cfg.web_url = Some("https://gitlawb.com".into());
+        assert!(cfg.validate().is_ok());
+
+        // Empty string is rejected.
+        let mut cfg = Config::parse_from(["gitlawb-node"]);
+        cfg.web_url = Some("".into());
+        assert!(cfg.validate().is_err(), "empty web_url must be rejected");
+
+        // Whitespace-only is rejected.
+        let mut cfg = Config::parse_from(["gitlawb-node"]);
+        cfg.web_url = Some("   ".into());
+        assert!(
+            cfg.validate().is_err(),
+            "whitespace-only web_url must be rejected"
+        );
+    }
+
+    #[test]
+    fn web_url_rejects_non_absolute_or_non_browser_urls() {
+        // Scheme-less host: parses nowhere, renders a broken View: link.
+        for bad in [
+            "gitlawb.com",
+            "not a url",
+            "ftp://files.example.com",
+            "javascript:alert(1)",
+            "https://", // no host
+        ] {
+            let mut cfg = Config::parse_from(["gitlawb-node"]);
+            cfg.web_url = Some(bad.into());
+            assert!(cfg.validate().is_err(), "web_url {bad:?} must be rejected");
+        }
+
+        // Query strings and fragments corrupt the appended repo path, since
+        // web_url is used as a raw string prefix (`?a=1` would swallow
+        // `/{owner}/{repo}` into the query).
+        for bad in [
+            "https://gitlawb.com?a=1",
+            "https://gitlawb.com/?utm_source=docs",
+            "https://gitlawb.com#section",
+            "https://gitlawb.com/#faq",
+        ] {
+            let mut cfg = Config::parse_from(["gitlawb-node"]);
+            cfg.web_url = Some(bad.into());
+            assert!(
+                cfg.validate().is_err(),
+                "web_url {bad:?} (query or fragment) must be rejected"
+            );
+        }
+
+        // Surrounding whitespace around a valid URL is tolerated.
+        let mut cfg = Config::parse_from(["gitlawb-node"]);
+        cfg.web_url = Some("  https://gitlawb.com  ".into());
+        assert!(
+            cfg.validate().is_ok(),
+            "padded-but-valid web_url must validate"
+        );
+
+        // Non-default ports and paths are fine.
+        let mut cfg = Config::parse_from(["gitlawb-node"]);
+        cfg.web_url = Some("http://localhost:8080/ui".into());
+        assert!(cfg.validate().is_ok(), "port+path web_url must validate");
+    }
 }

crates/gitlawb-node/src/main.rs

@@ -49,6 +49,7 @@ use state::AppState;
 struct DegradedState {
     node_did: String,
     db_startup: Arc<DbStartupStatus>,
+    web_url: Option<String>,
 }
 
 /// Two independent counters with no cross-field invariant — atomics, not a
@@ -154,6 +155,7 @@ async fn main() -> Result<()> {
         degraded_listener,
         node_did.to_string(),
         Arc::clone(&db_startup),
+        config.web_url.clone(),
         db_ready_rx,
         shutdown_tx.subscribe(),
     ));
@@ -780,11 +782,12 @@ async fn run_degraded_server(
     listener: TcpListener,
     node_did: String,
     db_startup: Arc<DbStartupStatus>,
+    web_url: Option<String>,
     mut db_ready_rx: watch::Receiver<bool>,
     mut shutdown_rx: watch::Receiver<bool>,
 ) -> Result<()> {
     let addr = listener.local_addr().ok();
-    let router = build_degraded_router(node_did, db_startup);
+    let router = build_degraded_router(node_did, db_startup, web_url);
     info!(?addr, "degraded HTTP server ready");
 
     axum::serve(listener, router)
@@ -801,10 +804,15 @@ async fn run_degraded_server(
     Ok(())
 }
 
-fn build_degraded_router(node_did: String, db_startup: Arc<DbStartupStatus>) -> Router {
+fn build_degraded_router(
+    node_did: String,
+    db_startup: Arc<DbStartupStatus>,
+    web_url: Option<String>,
+) -> Router {
     let state = DegradedState {
         node_did,
         db_startup,
+        web_url,
     };
     // Everything answers 503 with the same body — including /health and
     // /ready, so peer readiness probes and uptime monitors correctly see a
@@ -836,6 +844,9 @@ async fn degraded_node_info(State(state): State<DegradedState>) -> impl IntoResp
         obj.insert("name".into(), "gitlawb-node".into());
         obj.insert("version".into(), env!("CARGO_PKG_VERSION").into());
         obj.insert("did".into(), state.node_did.clone().into());
+        if let Some(web_url) = &state.web_url {
+            obj.insert("web_url".into(), web_url.clone().into());
+        }
     }
     (StatusCode::SERVICE_UNAVAILABLE, Json(body))
 }

crates/gitlawb-node/src/server.rs

@@ -531,7 +531,7 @@ async fn ready(State(state): State<AppState>) -> axum::response::Response {
 
 async fn node_info(State(state): State<AppState>) -> Json<serde_json::Value> {
     let p2p_peer_id = state.p2p.as_ref().map(|h| h.local_peer_id.to_string());
-    Json(json!({
+    let mut body = json!({
         "name": "gitlawb-node",
         "version": env!("CARGO_PKG_VERSION"),
         "did": state.node_did.to_string(),
@@ -540,7 +540,11 @@ async fn node_info(State(state): State<AppState>) -> Json<serde_json::Value> {
         "auth": "http-signature-rfc9421",
         "identity": "ed25519",
         "p2p_peer_id": p2p_peer_id,
-    }))
+    });
+    if let Some(web_url) = &state.config.web_url {
+        body["web_url"] = json!(web_url);
+    }
+    Json(body)
 }
 
 pub(crate) async fn stats(State(state): State<AppState>) -> Json<serde_json::Value> {

crates/gl/Cargo.toml

@@ -26,6 +26,7 @@ clap = { version = "4", features = ["derive", "env"] }
 dirs = "5"
 reqwest = { workspace = true }
 uuid = { workspace = true }
+url = { workspace = true }
 urlencoding = "2"
 alloy = { version = "1", default-features = false, features = [
     "contract",

crates/gl/src/mirror.rs

@@ -134,7 +134,11 @@ pub async fn run(args: MirrorArgs) -> Result<()> {
     println!();
     println!("✓ Mirror complete: {name}");
     println!("  Clone:  git clone {gitlawb_url}");
-    println!("  View:   https://gitlawb.com/{owner_short}/{name}");
+    // Only print View: when the node advertises a web_url — self-hosted nodes
+    // without a web front-end would otherwise produce a 404 link (#370).
+    if let Some(web_url) = crate::repo::fetch_node_web_url(&args.node).await {
+        println!("  View:   {web_url}/{owner_short}/{name}");
+    }
 
     Ok(())
 }