Shopify的代理商-商业类过滤器不过滤. 我们查了190个店.

Since 2026 every Shopify storefront answers an agent-commerce endpoint at , advertised at . Merchants did not turn it on and it is not in their admin. It speaks the Universal Commerce Protocol over JSON-RPC, and the tool that matters is : an AI shopping agent asks a store for its catalogue and gets structured product data back - integer prices in minor units with a currency, variants, SKUs, canonical URLs, and a Shopify taxonomy category per product. Fetch the tool list from any store and declares , an array of strings documented as "category filters combined with OR logic", next to . So an agent should be able to ask for running shoes and get running shoes. We were about to write a paragraph about what it costs a merchant to leave the category field blank. Then we tried it. Method 200 stores, drawn deterministically from a corpus of 10,099 known Shopify storefronts: sort the hostnames, take every Nth. Reproducible, so nobody has to take "we picked 200 stores" on trust. Run on 2 September 2026. Every store got the same five calls, 10 products requested each time: # Call Filter sent A working filter would 1 Control none return products 2 Impossible category return nothing 3 The store's own category a category the control's products carry return at least that product 4 Same, unwrapped the bare id without the other form an agent would try 5 Price control return nothing - nothing costs a cent Calls 2 and 3 only mean something together. Call 2 alone cannot distinguish "the filter is ignored" from "the filter rejects everything". Those are opposite findings, and both happen. The query matters more than it looks. Generic words ("gift", "set", "new") surface a catalogue's odd corners rather than its catalogue, and produce numbers that are measured honestly and still wrong. Every query here is three words from one of the store's own product titles, read from its public . Result 190 stores answered. What the store did with Stores Ignored it - the impossible category returned the full unfiltered set 186 Rejected everything - zero for every value, including its own products' category 4 Filtered correctly - impossible category empty, own category not 0 Of the 200 sampled, 10 could not be read: eight served no product feed to build a query from, two matched nothing for their own product title. 177 of the 190 returned at least one product carrying a taxonomy category, so this is not a missing-data story. The category is there. The filter does not use it. The control is the whole reason this is publishable A null result is worth nothing unless you can show the request worked. The control is , sent in the same envelope to the same store with one field changed. On 150 of 190 stores, of one cent correctly returned nothing. On 148 of those, the very same request that honoured price ignored the category. One field in moves the result and the other does not, in the same call, on the same store. If nothing had moved, the right conclusion would have been that we were sending it wrong. The bug we shipped first The first full run reported 177 stores refusing the request outright, and it was about to be written up as a discovery. It was our bug. A product comes back with objects. is declared as an array of strings. We were passing the object straight back in, violating the endpoint's own schema, and calling its entirely correct refusal a finding about Shopify. Taking fixed it, and call 4 exists because of it: if neither the wrapped identifier nor the bare one narrows anything, "you sent it wrong" stops being available as an explanation. This is the exact failure this kind of post usually ships with, and the only defence is publishing the rows. What it does and does not mean It does not mean an uncategorised product is invisible to agents. Nothing is being filtered out of anything, so a blank category excludes you from nothing. That was the sentence we expected to write, and it is false. It does mean an agent cannot narrow a catalogue search by category today, whatever the schema says, on any of the 190 stores we could read. It is not a complaint about Shopify. UCP shipped in 2026; a schema arriving before every part of its behaviour is ordinary for a young protocol doing a hard thing. The lesson is older than agentic commerce: test what an endpoint does rather than reading what it declares. Reproduce it in one call Pick any Shopify domain: Run it with and without the block and compare the counts. Calling the endpoint requires serving a UCP platform profile the store can fetch; ours declares empty , because a scanner takes no payments. All 190 readings, one row per store - domain, query, products returned for each of the five calls, and the verdict - are in filter-survey.csv. Every row names a domain you can re-run yourself, which is the point of publishing it. Originally published at shelfglance.com/research/ucp-category-filter, where the corpus of 10,099 scanned storefronts lives.