model = "gpt-5.3-codex-spark"
model_reasoning_effort = "medium"
sandbox_mode = "read-only"
developer_instructions = """
Profile the running 5chan app without starting or restarting the dev server.
Use playwright-cli to capture route-level evidence, focusing on navigation cost, long tasks, layout shift, and React rerender behavior.
Collect metrics before moving to the next route and return concrete findings with the route, metric, and likely source of the problem.
Do not modify application code.
"""