Probes Pixir's OpenAI Responses hosted web_search path.
This is a manual, opt-in, real-network smoke. It verifies request shaping and whether the active backend/model emits Provider-hosted web search evidence. It does not use Pixir local browser automation and does not treat search output as Pixir's source of truth.
Usage:
mix pixir.smoke.web_search --dry-run --json
mix pixir.smoke.web_search --json
mix pixir.smoke.web_search --model gpt-5.5 --reasoning-effort low --json
mix pixir.smoke.web_search --search-context-size low --json
mix pixir.smoke.web_search --helpOptions:
--model MODEL- Provider model. Default:gpt-5.5.--reasoning-effort EFFORT- one oflow,medium,high,xhigh. Default:low.--search-context-size SIZE- hosted web search context size:low,medium, orhigh. Default:low.--query TEXT- search prompt. Default asks for OpenAI's web search docs.--dry-run- validate and print the planned request shape without auth/network.--json- print machine-readable evidence or errors.--help- print this help and exit.