mcp

type BrowserInput struct {
	URL       string `json:"url,omitempty" jsonschema:"the URL to open (browser_navigate)"`
	Ref       string `json:"ref,omitempty" jsonschema:"element ref from the snapshot, e.g. @e5 (browser_click/browser_type)"`
	Text      string `json:"text,omitempty" jsonschema:"text to type (browser_type)"`
	Key       string `json:"key,omitempty" jsonschema:"key to press, e.g. Enter, Tab, Escape (browser_press)"`
	Direction string `json:"direction,omitempty" jsonschema:"up or down (browser_scroll)"`
	Full      bool   `json:"full,omitempty" jsonschema:"return the full page snapshot, not just interactive elements (browser_snapshot)"`
	Question  string `json:"question,omitempty" jsonschema:"what to look for in the screenshot (browser_vision)"`
}

type BrowserOutput struct {
	Snapshot     string `json:"snapshot,omitempty"`
	ElementCount int    `json:"element_count,omitempty"`
}

type ComputerElement struct {
	Index int    `json:"element_index"`
	Role  string `json:"role"`
	Label string `json:"label"`
}

type ComputerUseInput struct {
	Action         string   `` /* 165-byte string literal not displayed */
	Mode           string   `json:"mode,omitempty" jsonschema:"capture mode: som (default),vision,ax"`
	App            string   `` /* 192-byte string literal not displayed */
	MaxElements    int      `json:"max_elements,omitempty" jsonschema:"cap on returned AX elements (default 100, max 1000)"`
	Element        int      `json:"element,omitempty" jsonschema:"1-based SOM index from the last capture (preferred over coordinates)"`
	Coordinate     []int    `json:"coordinate,omitempty" jsonschema:"pixel [x,y]; use only when no element index is available"`
	Button         string   `json:"button,omitempty" jsonschema:"left,right,middle"`
	Modifiers      []string `json:"modifiers,omitempty" jsonschema:"modifier keys held during the action"`
	FromElement    int      `json:"from_element,omitempty"`
	ToElement      int      `json:"to_element,omitempty"`
	FromCoordinate []int    `json:"from_coordinate,omitempty"`
	ToCoordinate   []int    `json:"to_coordinate,omitempty"`
	Direction      string   `json:"direction,omitempty" jsonschema:"up,down,left,right"`
	Amount         int      `json:"amount,omitempty" jsonschema:"scroll wheel ticks (default 3)"`
	Value          string   `json:"value,omitempty" jsonschema:"value for set_value"`
	Text           string   `json:"text,omitempty" jsonschema:"text to type"`
	Keys           string   `json:"keys,omitempty" jsonschema:"key combo, e.g. cmd+s, ctrl+alt+t, return"`
	Seconds        float64  `json:"seconds,omitempty" jsonschema:"seconds to wait (max 30)"`
	RaiseWindow    bool     `json:"raise_window,omitempty"`
	CaptureAfter   bool     `json:"capture_after,omitempty" jsonschema:"take a follow-up capture after the action"`
}

type ComputerUseOutput struct {
	Summary   string            `json:"summary"`
	Elements  []ComputerElement `json:"elements,omitempty"`
	ImageMIME string            `json:"image_mime_type,omitempty"`
}

type ShellJobInfo struct {
	ID      string
	Script  string
	Status  string // running | completed | failed
	Running bool
	// Backgrounded is true for jobs that run detached from a turn — started via
	// bash_background, or a foreground command the user backgrounded with Ctrl+B.
	// A normal foreground command (consumed inline by the turn) is false.
	Backgrounded bool
}

type ShellJobs struct {
	// contains filtered or unexported fields
}

type StickyContext struct {
	PID       int
	WindowID  int
	SessionID string
	Desktop   bool // true after a desktop-scope capture: act by screen-absolute pixel, no window
	// Explicit marks a target the model deliberately chose — open_app, focus_app,
	// or capture(app=...) — as opposed to whatever happened to be frontmost. A
	// plain capture reuses an explicit target instead of re-detecting frontmost,
	// so "open_app then capture" sees the app just opened, not e.g. a mounted
	// DMG's Finder window that stole the front.
	Explicit bool
}