Files
BrowserOS/apps/cli/cmd/interact.go
Nikhil b7e63a4a1f feat: add browseros-cli Go CLI for browser automation (#421)
* feat: add browseros-cli Go CLI for browser automation

Implements a full-featured CLI that communicates with the BrowserOS MCP
server over JSON-RPC 2.0 / StreamableHTTP. Covers all 54 MCP tools across
10 categories with a hybrid command structure (flat verbs for hot-path
commands, grouped noun-verb for resource management).

- MCP client with initialize + tools/call pattern, thread-safe request IDs
- Dual output: human-readable default, --json for structured/piped usage
- Implicit active page resolution with --page override
- 21 command files: open, nav, snap, click, fill, scroll, eval, ss, pdf,
  dom, wait, dialog, pages, window, bookmark, history, group, health, info
- Cobra CLI framework with fatih/color for terminal formatting

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* test: add end-to-end integration tests for browseros-cli

Go integration tests gated by `//go:build integration` that exercise the
CLI binary against a running BrowserOS server. Tests build the binary,
run commands via exec.Command, and verify JSON output.

Covers: health, version, page lifecycle (open → text → snap → eval →
screenshot → nav → reload → close), active page, info, error handling,
and invalid page ID rejection. Skips gracefully when no server is running.

Run with: go test -tags integration -v ./...

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat: add init command and fix MCP client bugs

- Add `browseros-cli init` command that prompts for the server URL,
  verifies connectivity, and saves to ~/.config/browseros-cli/config.json
- Config priority: --server flag > BROWSEROS_URL env > config file > default
- Fix Accept header: include text/event-stream (required by StreamableHTTPTransport)
- Fix nil args: send empty object {} instead of null for tools with no params
- Update error messages to suggest `browseros-cli init` on connection failure

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* docs: add README for browseros-cli with setup, usage, and testing guide

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: always send arguments object in MCP tools/call

Go's json omitempty omits empty maps, causing the arguments field to be
missing from tools/call requests. The MCP SDK requires arguments to be
an object (even empty {}), not undefined. Remove omitempty from the tag.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat: update help menu to be have groups

* refactor: replace hand-rolled MCP client with official Go SDK

Switch from custom JSON-RPC implementation to the official
github.com/modelcontextprotocol/go-sdk. This removes all hand-rolled
protocol types (jsonrpcRequest, jsonrpcResponse, RPCError, etc.) and
uses the SDK's StreamableClientTransport with DisableStandaloneSSE
for clean CLI process lifecycle.

Also adds URL normalization/validation, config command, and
updates init/README to reference YAML config.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-05 14:49:45 -08:00

176 lines
4.3 KiB
Go

package cmd
import (
"fmt"
"strings"
"browseros-cli/output"
"github.com/spf13/cobra"
)
func init() {
hoverCmd := &cobra.Command{
Use: "hover <element>",
Annotations: map[string]string{"group": "Input:"},
Short: "Hover over an element",
Args: cobra.ExactArgs(1),
Run: elementAction("hover"),
}
focusCmd := &cobra.Command{
Use: "focus <element>",
Annotations: map[string]string{"group": "Input:"},
Short: "Focus an element",
Args: cobra.ExactArgs(1),
Run: elementAction("focus"),
}
checkCmd := &cobra.Command{
Use: "check <element>",
Annotations: map[string]string{"group": "Input:"},
Short: "Check a checkbox or radio button",
Args: cobra.ExactArgs(1),
Run: elementAction("check"),
}
uncheckCmd := &cobra.Command{
Use: "uncheck <element>",
Annotations: map[string]string{"group": "Input:"},
Short: "Uncheck a checkbox",
Args: cobra.ExactArgs(1),
Run: elementAction("uncheck"),
}
selectCmd := &cobra.Command{
Use: "select <element> <value>",
Annotations: map[string]string{"group": "Input:"},
Short: "Select a dropdown option",
Args: cobra.MinimumNArgs(2),
Run: func(cmd *cobra.Command, args []string) {
var element int
if _, err := fmt.Sscanf(args[0], "%d", &element); err != nil {
output.Errorf(3, "invalid element ID: %s", args[0])
}
value := strings.Join(args[1:], " ")
c := newClient()
pageID, err := resolvePageID(c)
if err != nil {
output.Error(err.Error(), 2)
}
result, err := c.CallTool("select_option", map[string]any{
"page": pageID,
"element": element,
"value": value,
})
if err != nil {
output.Error(err.Error(), 1)
}
if jsonOut {
output.JSON(result)
} else {
output.Confirm(result.TextContent())
}
},
}
dragCmd := &cobra.Command{
Use: "drag <source> --to <target>",
Annotations: map[string]string{"group": "Input:"},
Short: "Drag from one element to another",
Args: cobra.ExactArgs(1),
Run: func(cmd *cobra.Command, args []string) {
var source int
if _, err := fmt.Sscanf(args[0], "%d", &source); err != nil {
output.Errorf(3, "invalid source element: %s", args[0])
}
target, _ := cmd.Flags().GetInt("to")
c := newClient()
pageID, err := resolvePageID(c)
if err != nil {
output.Error(err.Error(), 2)
}
result, err := c.CallTool("drag", map[string]any{
"page": pageID,
"sourceElement": source,
"targetElement": target,
})
if err != nil {
output.Error(err.Error(), 1)
}
if jsonOut {
output.JSON(result)
} else {
output.Confirm(result.TextContent())
}
},
}
dragCmd.Flags().Int("to", 0, "Target element ID")
_ = dragCmd.MarkFlagRequired("to")
uploadCmd := &cobra.Command{
Use: "upload <element> <file...>",
Annotations: map[string]string{"group": "Input:"},
Short: "Upload files to a file input",
Args: cobra.MinimumNArgs(2),
Run: func(cmd *cobra.Command, args []string) {
var element int
if _, err := fmt.Sscanf(args[0], "%d", &element); err != nil {
output.Errorf(3, "invalid element ID: %s", args[0])
}
c := newClient()
pageID, err := resolvePageID(c)
if err != nil {
output.Error(err.Error(), 2)
}
result, err := c.CallTool("upload_file", map[string]any{
"page": pageID,
"element": element,
"files": args[1:],
})
if err != nil {
output.Error(err.Error(), 1)
}
if jsonOut {
output.JSON(result)
} else {
output.Confirm(result.TextContent())
}
},
}
rootCmd.AddCommand(hoverCmd, focusCmd, checkCmd, uncheckCmd, selectCmd, dragCmd, uploadCmd)
}
// elementAction creates a simple element-based tool command.
func elementAction(toolName string) func(*cobra.Command, []string) {
return func(cmd *cobra.Command, args []string) {
var element int
if _, err := fmt.Sscanf(args[0], "%d", &element); err != nil {
output.Errorf(3, "invalid element ID: %s", args[0])
}
c := newClient()
pageID, err := resolvePageID(c)
if err != nil {
output.Error(err.Error(), 2)
}
result, err := c.CallTool(toolName, map[string]any{
"page": pageID,
"element": element,
})
if err != nil {
output.Error(err.Error(), 1)
}
if jsonOut {
output.JSON(result)
} else {
output.Confirm(result.TextContent())
}
}
}