Top-of-search placement optimizer

Read https://www.sellermate.ai/api-docs first. It documents the SellerMate Public API: REST over HTTPS, X-API-Key auth, and every tool with its parameters is on that page. Every tool is POST https://api.sellermate.ai/public/v1/tools/{name} with a JSON body.

Build me a placement optimizer for Sponsored Products in one account.

- Pull the last 30 days of placement data with get_placement_performance
- For each campaign, compare ACoS and conversion rate at top of search versus product pages and rest of search
- Propose a placement bid adjustment: raise top-of-search by up to [25] points where its ACoS is at least [20]% better than the campaign average and it has at least [20] orders; lower it by up to 25 points where it is worse
- Print a table: campaign, current adjustment, proposed adjustment, reason
- With --apply, send the changes through update_campaign using dynamic_bidding.placementBidding, keeping all other settings. Without --apply, change nothing.

Resolve the account with get_user_context.

Rules:
- My key is in the SELLERMATE_API_KEY environment variable. Send it as the X-API-Key header. Never hard-code it or log it.
- Call get_user_context first and use the accounts it returns. Don't invent account ids.
- Report tools are paginated (page, page_size up to 500, pagination.hasMore). Walk every page.
- On a 429, wait for the Retry-After header and retry. On a 401 or 403, stop and tell me.
- Show me the plan and the code before running anything that writes.

Stack: Python 3 with requests.