Developers

verify

verify lets a search run additional passes. Each pass excludes what earlier passes returned, so a second pass reaches memories the first did not.

Supported on Tablet 2 and newer. Asking an engine that does not implement it is refused before the call is made, so you are never charged for a pass that silently did nothing.

An integer 0-3 on search and recall. It is the number of additional passes, so 3 allows four retrievals. Default 0.

hits = mem.search("what did I eat", verify=3)
# the SDKs hand back the memories; `verify_used` is on the HTTP response (curl tab)
const hits = await mem.search("what did I eat", undefined, 10, { verify: 3 });
// the SDKs hand back the memories; `verify_used` is on the HTTP response (curl tab)
let hits = mem.search_opts("what did I eat", None, 10,
                            &SearchOpts { verify: Some(3), ..Default::default() }).await?;
// the SDKs hand back the memories; `verify_used` is on the HTTP response (curl tab)
curl -X POST https://api.wontopos.com/api/v1/memory/search \
  -H "X-API-Key: $WOS_KEY" -H "Content-Type: application/json" \
  -d '{"user_id":"alice","query":"what did I eat","verify":3}'
# → {"memories":[…], "verify_used":1}

No language model runs in that loop

Passes carry the ids already returned; the engine excludes them and searches past them. The query is not reformulated, so results are deterministic for a given request and no model credentials are involved. Your code decides whether to spend another pass.

What you send and what comes back

CallWhat it does
verify0 to 3. Additional passes permitted. Out of range is rejected with a 400 rather than quietly clamped.
verify_usedHow many additional passes were actually made. Can be lower than what you asked for.

Passes stop early when one returns nothing new, and unused passes are not billed. If a later pass fails, the results gathered so far are returned.

Extra passes can lower accuracy when the first pass already held the answer - single-session-user questions on LongMemEval-S drop 4.2 points. The gain scales with how often one retrieval misses, so it is larger on big stores.