memo_consolidate
Find near-duplicate memories and get merge proposals without modifying the corpus. Group related items into clusters with similarity thresholds to identify consolidation candidates.
Instructions
Detect near-duplicate clusters and propose merges.
Read-only — returns proposals without modifying the corpus.
Uses the AdvancedConsolidator under the hood (same as
memo_consolidate_list_archived). With client sampling enabled,
merge synthesis runs on the calling model up to
MEMO_SAMPLING_MAX_CALLS (see synthesizer field). max_clusters
bounds how many clusters come back; a single cluster's member list
is bounded separately by member_limit -- same-topic memories
cluster by design, so one cluster can hold most of the corpus.
Both defaults are derived from MEMO_MCP_RESPONSE_BUDGET_TOKENS rather
than picked for round numbers: a returned member carries a 600-char
body_preview, so the response costs roughly
max_clusters * member_limit * 850 chars and the previous 20 x 20
spent ~47k tokens against a 10k cap -- 20 clusters cannot be returned
with any useful member detail at all. 10 x 2 measures 3,978 tokens on
the conformance corpus and ~9,039 projected for a corpus whose bodies
actually reach the 600-char preview cap. Two sample members are what
it takes to SEE a duplicate; total still reports the cluster's real
size, and memo_get fetches any member by id. Raise either argument
to see more and accept a larger response (the budget middleware
refuses one that overruns rather than silently truncating it).
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "memo_consolidate"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Optional filter by memory type. | |
| threshold | No | Cosine similarity threshold (default 0.85). | |
| max_clusters | No | Clusters to process and return. Each one costs a member list plus a merge proposal, so this is the dominant term in the response size. | |
| member_limit | No | Sample members returned per cluster. A cluster's true size always comes back in `total`; `truncated` says whether any members were dropped. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||