feat(computer-use): background focus-safe backend — set_value, structured windows, MIME detection

Extends the cua-driver computer-use backend to drive backgrounded macOS
windows without stealing keyboard or mouse focus from the foreground app.
All changes target the cua-driver MCP backend and the shared dispatcher.

## cua_backend.py

**Window-aware capture**: capture() now calls list_windows + get_window_state
instead of the removed capture tool. Prefers structuredContent.windows
(MCP 2024-11-05+ cua-driver) for zero-parse window enumeration; falls back
to regex-parsed text for older builds. Stores the selected (pid, window_id)
as sticky context so subsequent action calls do not need a redundant round-trip.

**Action routing**: click/scroll/type_text/key all carry the sticky pid
(and window_id for element-indexed clicks). type_text routes through
type_text_chars (individual key events) rather than AX attribute write --
WebKit AXTextFields reject attribute writes from backgrounded processes.

**Key parsing**: _parse_key_combo splits cmd+s-style strings into
(key, [modifiers]) and routes to hotkey (modifier present) or
press_key (bare key) -- cua-driver actual tool names.

**set_value method**: new set_value(value, element) calls the cua-driver
set_value MCP tool. For AXPopUpButton / HTML select in a backgrounded Safari,
AXPress opens the native macOS popup which closes immediately when the app is
non-frontmost; set_value AX-presses the matching child option directly
(no menu required, no focus steal).

**focus_app**: reimplemented as a pure window-selector (enumerates
list_windows, sets sticky pid/window_id) without ever raising the window
or stealing focus.

**list_apps**: fixed tool name from listApps to list_apps; handles plain-text
response via regex when structured data is absent.

**Structured-content extraction**: _extract_tool_result now surfaces
structuredContent from MCP results, enabling the list_windows window array
without text parsing.

**Helpers**: _parse_windows_from_text, _parse_elements_from_tree,
_split_tree_text, _parse_key_combo extracted as module-level functions.

## schema.py

Added set_value to the action enum with a description explaining when to
prefer it over click (select/popup elements, sliders, no focus steal).
Added value field for set_value payloads.

## tool.py

Routed set_value action through _dispatch to backend.set_value.
Added set_value to _DESTRUCTIVE_ACTIONS (approval-gated).
Fixed MIME-type detection in _capture_response: cua-driver may return
JPEG; detect from base64 magic bytes (/9j/ -> image/jpeg, else image/png)
rather than hardcoding image/png.

## agent/display.py + run_agent.py

Guard _detect_tool_failure and result-preview logic against non-string
function_result values: multimodal tool results (dicts with _multimodal=True)
are not string-sliceable; treat them as successes and fall back to str()
for length/preview.
This commit is contained in:
ddupont 2026-04-24 13:39:12 -07:00 committed by Teknium
parent 850413f120
commit e31f3b3c56
5 changed files with 363 additions and 75 deletions

View file

@ -10584,9 +10584,15 @@ class AIAgent:
logger.error("handle_function_call raised for %s: %s", function_name, tool_error, exc_info=True)
tool_duration = time.time() - tool_start_time
result_preview = function_result if self.verbose_logging else (
function_result[:200] if len(function_result) > 200 else function_result
)
if isinstance(function_result, str):
result_preview = function_result if self.verbose_logging else (
function_result[:200] if len(function_result) > 200 else function_result
)
_result_len = len(function_result)
else:
# Multimodal dict result (_multimodal=True) — not sliceable as string
result_preview = function_result
_result_len = len(str(function_result))
# Log tool errors to the persistent error log so [error] tags
# in the UI always have a corresponding detailed entry on disk.
@ -10604,7 +10610,7 @@ class AIAgent:
if _is_error_result:
logger.warning("Tool %s returned error (%.2fs): %s", function_name, tool_duration, result_preview)
else:
logger.info("tool %s completed (%.2fs, %d chars)", function_name, tool_duration, len(function_result))
logger.info("tool %s completed (%.2fs, %d chars)", function_name, tool_duration, _result_len)
if not _execution_blocked and self.tool_progress_callback:
try:
@ -10663,7 +10669,8 @@ class AIAgent:
print(f" ✅ Tool {i} completed in {tool_duration:.2f}s")
print(self._wrap_verbose("Result: ", function_result))
else:
response_preview = function_result[:self.log_prefix_chars] + "..." if len(function_result) > self.log_prefix_chars else function_result
_fr_str = function_result if isinstance(function_result, str) else str(function_result)
response_preview = _fr_str[:self.log_prefix_chars] + "..." if len(_fr_str) > self.log_prefix_chars else _fr_str
print(f" ✅ Tool {i} completed in {tool_duration:.2f}s - {response_preview}")
if self._interrupt_requested and i < len(assistant_message.tool_calls):