MCP/CDP: unify node registration

This fixes a bug in MCP where interactive elements were not assigned
a backendNodeId, preventing agents from clicking or filling them. Also
extracts link collection to a shared browser module.
This commit is contained in:
Adrià Arrufat
2026-03-26 23:49:42 +09:00
parent a0dd14aaad
commit 7e778a17d6
5 changed files with 82 additions and 25 deletions

View File

@@ -36,6 +36,7 @@ pub const InteractivityType = enum {
}; };
pub const InteractiveElement = struct { pub const InteractiveElement = struct {
backendNodeId: ?u32 = null,
node: *Node, node: *Node,
tag_name: []const u8, tag_name: []const u8,
role: ?[]const u8, role: ?[]const u8,
@@ -55,6 +56,11 @@ pub const InteractiveElement = struct {
pub fn jsonStringify(self: *const InteractiveElement, jw: anytype) !void { pub fn jsonStringify(self: *const InteractiveElement, jw: anytype) !void {
try jw.beginObject(); try jw.beginObject();
if (self.backendNodeId) |id| {
try jw.objectField("backendNodeId");
try jw.write(id);
}
try jw.objectField("tagName"); try jw.objectField("tagName");
try jw.write(self.tag_name); try jw.write(self.tag_name);
@@ -123,6 +129,15 @@ pub const InteractiveElement = struct {
} }
}; };
/// Populate backendNodeId on each interactive element by registering
/// their nodes in the given registry. Works with both CDP and MCP registries.
pub fn registerNodes(elements: []InteractiveElement, registry: anytype) !void {
for (elements) |*el| {
const registered = try registry.register(el.node);
el.backendNodeId = registered.id;
}
}
/// Collect all interactive elements under `root`. /// Collect all interactive elements under `root`.
pub fn collectInteractiveElements( pub fn collectInteractiveElements(
root: *Node, root: *Node,

54
src/browser/links.zig Normal file
View File

@@ -0,0 +1,54 @@
// Copyright (C) 2023-2026 Lightpanda (Selecy SAS)
//
// Francis Bouvier <francis@lightpanda.io>
// Pierre Tachoire <pierre@lightpanda.io>
//
// This program is free software: you can redistribute it and/or modify
// it under the terms of the GNU Affero General Public License as
// published by the Free Software Foundation, either version 3 of the
// License, or (at your option) any later version.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Affero General Public License for more details.
//
// You should have received a copy of the GNU Affero General Public License
// along with this program. If not, see <https://www.gnu.org/licenses/>.
const std = @import("std");
const Element = @import("webapi/Element.zig");
const Node = @import("webapi/Node.zig");
const Page = @import("Page.zig");
const Selector = @import("webapi/selector/Selector.zig");
const Allocator = std.mem.Allocator;
/// Collect all links (href attributes from anchor tags) under `root`.
/// Returns a slice of strings allocated with `arena`.
pub fn collectLinks(arena: Allocator, root: *Node, page: *Page) ![]const []const u8 {
var links: std.ArrayList([]const u8) = .empty;
if (Selector.querySelectorAll(root, "a[href]", page)) |list| {
defer list.deinit(page._session);
for (list._nodes) |node| {
if (node.is(Element.Html.Anchor)) |anchor| {
const href = anchor.getHref(page) catch |err| {
@import("../lightpanda.zig").log.err(.app, "resolve href failed", .{ .err = err });
continue;
};
if (href.len > 0) {
try links.append(arena, href);
}
}
}
} else |err| {
@import("../lightpanda.zig").log.err(.app, "query links failed", .{ .err = err });
return err;
}
return links.items;
}

View File

@@ -135,17 +135,10 @@ fn getInteractiveElements(cmd: anytype) !void {
page.document.asNode(); page.document.asNode();
const elements = try interactive.collectInteractiveElements(root, cmd.arena, page); const elements = try interactive.collectInteractiveElements(root, cmd.arena, page);
try interactive.registerNodes(elements, &bc.node_registry);
// Register nodes so nodeIds are valid for subsequent CDP calls.
var node_ids: std.ArrayList(Node.Id) = try .initCapacity(cmd.arena, elements.len);
for (elements) |el| {
const registered = try bc.node_registry.register(el.node);
node_ids.appendAssumeCapacity(registered.id);
}
return cmd.sendResult(.{ return cmd.sendResult(.{
.elements = elements, .elements = elements,
.nodeIds = node_ids.items,
}, .{}); }, .{});
} }
@@ -308,7 +301,6 @@ test "cdp.lp: getInteractiveElements" {
const result = (try ctx.getSentMessage(0)).?.object.get("result").?.object; const result = (try ctx.getSentMessage(0)).?.object.get("result").?.object;
try testing.expect(result.get("elements") != null); try testing.expect(result.get("elements") != null);
try testing.expect(result.get("nodeIds") != null);
} }
test "cdp.lp: getStructuredData" { test "cdp.lp: getStructuredData" {

View File

@@ -35,6 +35,7 @@ pub const markdown = @import("browser/markdown.zig");
pub const SemanticTree = @import("SemanticTree.zig"); pub const SemanticTree = @import("SemanticTree.zig");
pub const CDPNode = @import("cdp/Node.zig"); pub const CDPNode = @import("cdp/Node.zig");
pub const interactive = @import("browser/interactive.zig"); pub const interactive = @import("browser/interactive.zig");
pub const links = @import("browser/links.zig");
pub const forms = @import("browser/forms.zig"); pub const forms = @import("browser/forms.zig");
pub const actions = @import("browser/actions.zig"); pub const actions = @import("browser/actions.zig");
pub const structured_data = @import("browser/structured_data.zig"); pub const structured_data = @import("browser/structured_data.zig");

View File

@@ -203,24 +203,13 @@ const ToolStreamingText = struct {
log.err(.mcp, "markdown dump failed", .{ .err = err }); log.err(.mcp, "markdown dump failed", .{ .err = err });
}, },
.links => { .links => {
if (Selector.querySelectorAll(self.page.document.asNode(), "a[href]", self.page)) |list| { if (lp.links.collectLinks(self.page.call_arena, self.page.document.asNode(), self.page)) |links| {
defer list.deinit(self.page._session);
var first = true; var first = true;
for (list._nodes) |node| { for (links) |href| {
if (node.is(Element.Html.Anchor)) |anchor| {
const href = anchor.getHref(self.page) catch |err| {
log.err(.mcp, "resolve href failed", .{ .err = err });
continue;
};
if (href.len > 0) {
if (!first) try w.writeByte('\n'); if (!first) try w.writeByte('\n');
try w.writeAll(href); try w.writeAll(href);
first = false; first = false;
} }
}
}
} else |err| { } else |err| {
log.err(.mcp, "query links failed", .{ .err = err }); log.err(.mcp, "query links failed", .{ .err = err });
} }
@@ -417,6 +406,12 @@ fn handleInteractiveElements(server: *Server, arena: std.mem.Allocator, id: std.
log.err(.mcp, "elements collection failed", .{ .err = err }); log.err(.mcp, "elements collection failed", .{ .err = err });
return server.sendError(id, .InternalError, "Failed to collect interactive elements"); return server.sendError(id, .InternalError, "Failed to collect interactive elements");
}; };
lp.interactive.registerNodes(elements, &server.node_registry) catch |err| {
log.err(.mcp, "node registration failed", .{ .err = err });
return server.sendError(id, .InternalError, "Failed to register element nodes");
};
var aw: std.Io.Writer.Allocating = .init(arena); var aw: std.Io.Writer.Allocating = .init(arena);
try std.json.Stringify.value(elements, .{}, &aw.writer); try std.json.Stringify.value(elements, .{}, &aw.writer);