common,server: handle bracketed IPv6 literals in URL authority (#25140)

* common,server: handle bracketed IPv6 literals in URL authority

Parse the [host]:port form (RFC 3986) and bracket IPv6 hosts when
formatting a URL authority: listening log, proxy Host header, proxy
log, client rebuild. The per-request remote_addr stays bare.

* common: restore unsupported scheme throw in url parser

Address @ngxson review: keep the explicit reject in port resolution so
the block stays self-contained. Non-http(s) schemes still throw (also
gated at the top of common_http_parse_url).

diff --git a/common/http.h b/common/http.h
index d3daccd6bf483d4a69a09951b68f8b6c7ae0e3c8..e88bc6a5e4d4584b13596c2da90885c963ef45e8 100644 (file)
--- a/common/http.h
+++ b/common/http.h
@@ -11,6 +11,11 @@ struct common_http_url {
     std::string path;
 };
 
+// bracket an IPv6 literal host for a URL authority (RFC 3986)
+static std::string common_http_format_host(const std::string & host) {
+    return host.find(':') != std::string::npos ? "[" + host + "]" : host;
+}
+
 static common_http_url common_http_parse_url(const std::string & url) {
     common_http_url parts;
     auto scheme_end = url.find("://");
@@ -49,11 +54,28 @@ static common_http_url common_http_parse_url(const std::string & url) {
         parts.path = "/";
     }
 
-    auto colon_pos = parts.host.find(':');
+    // split the authority into host and optional port, a bracketed IPv6 literal keeps its inner colons (RFC 3986)
+    std::string port_str;
+    if (!parts.host.empty() && parts.host.front() == '[') {
+        auto close = parts.host.find(']');
+        if (close == std::string::npos) {
+            throw std::runtime_error("invalid IPv6 URL authority: " + parts.host);
+        }
+        auto after = parts.host.substr(close + 1);
+        if (!after.empty() && after.front() == ':') {
+            port_str = after.substr(1);
+        }
+        parts.host = parts.host.substr(1, close - 1);
+    } else {
+        auto colon_pos = parts.host.find(':');
+        if (colon_pos != std::string::npos) {
+            port_str = parts.host.substr(colon_pos + 1);
+            parts.host = parts.host.substr(0, colon_pos);
+        }
+    }
 
-    if (colon_pos != std::string::npos) {
-        parts.port = std::stoi(parts.host.substr(colon_pos + 1));
-        parts.host = parts.host.substr(0, colon_pos);
+    if (!port_str.empty()) {
+        parts.port = std::stoi(port_str);
     } else if (parts.scheme == "http") {
         parts.port = 80;
     } else if (parts.scheme == "https") {
@@ -83,7 +105,7 @@ static std::pair<httplib::Client, common_http_url> common_http_client(const std:
     }
 #endif
 
-    httplib::Client cli(parts.scheme + "://" + parts.host + ":" + std::to_string(parts.port));
+    httplib::Client cli(parts.scheme + "://" + common_http_format_host(parts.host) + ":" + std::to_string(parts.port));
 
     if (!parts.user.empty()) {
         cli.set_basic_auth(parts.user, parts.password);
@@ -95,5 +117,5 @@ static std::pair<httplib::Client, common_http_url> common_http_client(const std:
 }
 
 static std::string common_http_show_masked_url(const common_http_url & parts) {
-    return parts.scheme + "://" + (parts.user.empty() ? "" : "****:****@") + parts.host + parts.path;
+    return parts.scheme + "://" + (parts.user.empty() ? "" : "****:****@") + common_http_format_host(parts.host) + parts.path;
 }

diff --git a/tools/server/server-cors-proxy.h b/tools/server/server-cors-proxy.h
index 53a6909ed2f2fe137095c3a21c07d1f96dbd21dc..3600a33ec6476b7c668c8c511f7c8f1c3f958e31 100644 (file)
--- a/tools/server/server-cors-proxy.h
+++ b/tools/server/server-cors-proxy.h
@@ -39,7 +39,7 @@ static server_http_res_ptr proxy_request(const server_http_req & req, std::strin
         throw std::runtime_error("unsupported URL scheme in target URL: " + parsed_url.scheme);
     }
 
-    SRV_INF("proxying %s request to %s://%s:%i%s\n", method.c_str(), parsed_url.scheme.c_str(), parsed_url.host.c_str(), parsed_url.port, parsed_url.path.c_str());
+    SRV_INF("proxying %s request to %s://%s:%i%s\n", method.c_str(), parsed_url.scheme.c_str(), common_http_format_host(parsed_url.host).c_str(), parsed_url.port, parsed_url.path.c_str());
 
     std::map<std::string, std::string> headers;
     const std::string proxy_header_prefix = "x-llama-server-proxy-header-";

diff --git a/tools/server/server-http.cpp b/tools/server/server-http.cpp
index 21bed64c9258dc964e19aa596970fe9dde5bde26..bb88dda219802cb634e9cfd9daceff9bab40ae47 100644 (file)
--- a/tools/server/server-http.cpp
+++ b/tools/server/server-http.cpp
@@ -1,4 +1,5 @@
 #include "common.h"
+#include "http.h"
 #include "server-http.h"
 #include "server-stream.h"
 #include "server-common.h"
@@ -441,7 +442,7 @@ bool server_http_context::start() {
     srv->wait_until_ready();
 
     listening_address = is_sock ? string_format("unix://%s", hostname.c_str())
-                                : string_format("%s://%s:%d", is_ssl ? "https" : "http", hostname.c_str(), port);
+                                : string_format("%s://%s:%d", is_ssl ? "https" : "http", common_http_format_host(hostname).c_str(), port);
     return true;
 }
 

diff --git a/tools/server/server-models.cpp b/tools/server/server-models.cpp
index 81da00c0e02221118913cb1626f5b4568eff8559..2ee318f14469a0695e84302cc7f42f54a931b37d 100644 (file)
--- a/tools/server/server-models.cpp
+++ b/tools/server/server-models.cpp
@@ -1,4 +1,5 @@
 #include "server-common.h"
+#include "http.h"
 #include "server-models.h"
 #include "server-context.h"
 #include "server-stream.h"
@@ -2263,7 +2264,8 @@ server_http_proxy::server_http_proxy(
             }
             if (lowered == "host") {
                 bool is_default_port = (scheme == "https" && port == 443) || (scheme == "http" && port == 80);
-                req.set_header(key, is_default_port ? host : host + ":" + std::to_string(port));
+                const std::string url_host = common_http_format_host(host);
+                req.set_header(key, is_default_port ? url_host : url_host + ":" + std::to_string(port));
             } else {
                 req.set_header(key, value);
             }