create_crawl_task

io.github.lvpiggyqq/xcatcher · Verify this server

Create a crawl task for one or more X (Twitter) usernames. Side effects: creates a new task AND consumes points. If points are insufficient, upstream returns HTTP 402 with PAYMENT-REQUIRED (quote). This tool surfaces it as error.code=PAYMENT_REQUIRED with payment_required payload so agents can request spending approval, top up, then retry safely. Modes: - normal: Fast latest-post snapshot at scale (fresh-feed monitoring). Optimized for high-throughput batch retrieval. - deep: Deeper per-user collection/enrichment (typically slower; higher resource usage). Use when you need more than a quick latest-post snapshot. Performance note: Normal mode is optimized for a small latest-post snapshot per handle. Actual completeness and latency depend on X availability, upstream limits, and network conditions. Batching: For very large sets, split users into batches. Suggested upper bound per task: 500 users (configurable via MAX_USERS_PER_TASK). Reliability: - Use idempotency_key to make retries safe (avoid duplicate charges). - After creation, poll get_task_status every 5–10s until has_result=true. - Then call get_result_download_url (download still requires the same Bearer token).