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

@@ -54,7 +54,8 @@ uuid = { version = "1", features = ["v4"] }
 # http client
 reqwest = { version = "0.12", features = ["blocking", "json", "multipart", "rustls-tls"], default-features = false }
 # URL parsing (what reqwest::Url re-exports, so the shared redirect predicate can
-# take a parsed URL without pulling reqwest into gitlawb-core)
+# take a parsed URL without pulling reqwest into gitlawb-core; also used for the
+# absolute-browser-url validation on GITLAWB_WEB_URL in the node and CLI)
 url = "2"
 # HMAC
 hmac = "0.12"

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>,
@@ -728,7 +734,13 @@ impl Config {
     /// Cross-field boot validation. Single-field ranges are enforced by clap; this
     /// catches combinations that ship a denial-of-service under otherwise-valid
     /// values. Call once at startup and fail fast on `Err`.
-    pub fn validate(&self) -> Result<(), String> {
+    ///
+    /// `&mut self` is required so the validator can normalize `web_url` to
+    /// its canonical form after validation: the configured value is
+    /// advertised on public `GET /`, and any consumer reading
+    /// `config.web_url` later must see the same string that was actually
+    /// validated.
+    pub fn validate(&mut self) -> Result<(), String> {
         // A write pins one pooled connection for its whole duration (the
         // connection-affine advisory lock in repo_store::acquire_write), and
         // concurrent writes are capped at max_concurrent_git_pushes. If the pool
@@ -746,10 +758,84 @@ 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."
+                    ));
+                }
+            }
+            // Normalize to one canonical form so every consumer (the regular
+            // and degraded `GET /` handlers, anyone who reads
+            // `config.web_url` directly) sees the same string that was
+            // actually validated. The CLI's own defensive trim would paper
+            // over the divergence on the `View:` line, but that hides the
+            // bug from any other consumer that parses the value verbatim.
+            let canonical = raw
+                .trim()
+                .parse::<url::Url>()
+                .map(|u| u.to_string())
+                .map_err(|_| "is not a valid absolute URL".to_string())?;
+            if canonical != *raw {
+                self.web_url = Some(canonical);
+            }
+        }
         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, fragment, or userinfo — 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);
+/// and userinfo is rejected outright because the configured value is
+/// published on public `GET /` and reprinted on the CLI's `View:` line,
+/// so an accidentally configured password would land in public metadata,
+/// terminal scrollback, and CI logs.
+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(),
+        );
+    }
+    if !parsed.username().is_empty() || parsed.password().is_some() {
+        return Err(
+            "must not contain a username or password — it is advertised publicly and printed on the View: line"
+                .into(),
+        );
+    }
+    Ok(())
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
@@ -1375,7 +1461,7 @@ mod tests {
             .expect("default config must validate");
 
         // An under-sized pool relative to the push cap is rejected (20 < 32 + 8).
-        let under = Config::parse_from([
+        let mut under = Config::parse_from([
             "gitlawb-node",
             "--db-max-connections",
             "20",
@@ -1388,7 +1474,7 @@ mod tests {
         );
 
         // Exactly at the floor validates (40 == 32 + 8).
-        let at_floor = Config::parse_from([
+        let mut at_floor = Config::parse_from([
             "gitlawb-node",
             "--db-max-connections",
             "40",
@@ -1401,6 +1487,129 @@ mod tests {
         );
     }
 
+    #[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");
+
+        // Userinfo must be rejected: `web_url` is published on public
+        // `GET /` and reprinted on the CLI's `View:` line, so an
+        // accidentally configured password would land in public metadata,
+        // terminal scrollback, and CI logs. Reject username-only and
+        // user+password forms.
+        for bad in [
+            "https://user@example.com",
+            "https://user:secret@example.com",
+            "https://:secret@example.com",
+        ] {
+            let mut cfg = Config::parse_from(["gitlawb-node"]);
+            cfg.web_url = Some(bad.into());
+            assert!(
+                cfg.validate().is_err(),
+                "web_url {bad:?} (userinfo) must be rejected"
+            );
+        }
+    }
+
+    /// `validate()` accepts whitespace-padded input but the stored value
+    /// must match the canonical form actually validated, so every consumer
+    /// (the regular and degraded `GET /` handlers, anyone who reads
+    /// `config.web_url` directly) sees the same string. Without this, an
+    /// operator that sets `GITLAWB_WEB_URL="  https://git.example  "` boots
+    /// a node that advertises `"  https://git.example  "` on public
+    /// metadata — different from what was validated, different from what
+    /// any other consumer would parse.
+    #[test]
+    fn web_url_is_normalized_to_canonical_form_after_validation() {
+        // Padded input is rewritten to the canonical form. `url::Url`'s
+        // own `to_string` is what we use for the canonicalization, and
+        // it always appends a path-separator slash to a bare-host URL,
+        // so the stored value is `https://git.example/` (which is also
+        // what every browser would normalize the operator-typed form to).
+        let mut cfg = Config::parse_from(["gitlawb-node"]);
+        cfg.web_url = Some("  https://git.example  ".into());
+        cfg.validate().unwrap();
+        assert_eq!(
+            cfg.web_url.as_deref(),
+            Some("https://git.example/"),
+            "stored web_url must be the canonical form, not the operator-typed one"
+        );
+
+        // Already-canonical input is left alone after a no-op
+        // re-normalization — same form comes back out, so any consumer
+        // reading the stored value sees a stable string across calls.
+        let mut cfg = Config::parse_from(["gitlawb-node"]);
+        cfg.web_url = Some("https://git.example/".into());
+        cfg.validate().unwrap();
+        assert_eq!(cfg.web_url.as_deref(), Some("https://git.example/"));
+    }
+
     /// The DECLARED default, read off the parser rather than out of a parse.
     ///
     /// `Config::parse_from` consults the process environment, so on a host that