From 3edcce41c6a4c956af1b66e87e4bf7ea89a06c71 Mon Sep 17 00:00:00 2001 From: a2a-cloud Date: Mon, 8 Jun 2026 23:17:11 +0000 Subject: [PATCH] write README.md --- README.md | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 794551a..2fb8845 100644 --- a/README.md +++ b/README.md @@ -44,12 +44,13 @@ Returns fields include: {status, items, pages_visited, html_captures, screenshot An LLM-powered planner that iterates scrapes until a goal is satisfied or a safety/stop condition occurs. Inputs: - goal — natural-language target (e.g., "Collect quotes text and authors from the first 2 pages"). -- url — start page (absolute http/https). Same-origin only for all iterations. -- selectors — optional initial CSS selector map (defaults to {"title": "title"}). -- min_items — stop when this many items have been collected. -- max_iterations — planner budget (default 5, hard-capped at 3 improvements per runtime notes). -- per_pass_max_pages — pages per scrape pass (default 1, capped by agent config). +- start_url — start page (absolute http/https). Same-origin only for all iterations unless allowed_domains is provided. +- seed_selectors — optional initial CSS selector map (defaults to {"title": "title"}). +- max_steps — planner steps (hard-capped at 3 improvements). +- max_pages — pages per scrape pass (default 1, capped by agent config). +- max_runtime_seconds — total runtime budget across steps. - wait_seconds, output_format, headless, user_agent, respect_robots, rate_limit_seconds, screenshot — mirror scrape_website. +- allowed_domains — optional whitelist; else restricted to same-origin. Outputs: - status — ok | no_items | blocked_by_robots_txt | manual_intervention_required | browser_runtime_unavailable | error