TODO

P0

[Bug] Enforce single active desktop-control run (or a strict queue) so concurrent jobs cannot fight over the same mouse/keyboard/screen session.
[Bug] Fix run artifact collisions in setup_artifacts() (run_id is second-granularity, so two jobs in the same second can share/overwrite the same directory).
[Bug] Remove global logger handler clobbering in setup_logger() (logging.getLogger("screenjob").handlers.clear() breaks concurrent runs and can redirect logs to the wrong file).
More consistent clicks and more uses of enhance images.

Move ui.py into a seperate html file and js file.
Think harder using effort "medium" by default.
Decay old screenshots after 3 to 5 steps to save (1) tokens and (2) brain fuck in the agents.
[Bug] Validate disabled_tools against an allowlist and disallow disabling critical completion flow (task_complete) to avoid guaranteed step-limit failures.
[Bug] Improve execute_command cancellation/timeout handling to terminate full process trees, not only the parent shell process.

[Bug] Fix UI event style mapping mismatch (tool_called events are emitted, but UI color map expects tool_call).
[Idea] Reduce monitoring UI backend load by throttling websocket-triggered refreshes and avoiding full job/event re-fetch on every event.
[Idea] Add retention controls/pruning for old runs, screenshots, and DB rows.

Add Replay Mode; Ability to replay a session by reconstructing the screen from screenshots and overlaying tool calls and click and type events.
[Idea] Add lightweight analytics dashboards (success rate by objective category, avg steps/cost over time).