44,196 chunks behind a tool nobody routed to

Our unified search tool says 'prefer this over individual tools'. Our entire research corpus was not one of its layers. On six topics that live only there, the direct search won 6 of 6. And 75% of our memory had never been retrieved even once.

1 Nov 2026 · 2 min read

Our agents have one recommended way to look things up: a unified search across memory, knowledge, code, docs, sessions and plans. Its description says “prefer this over individual tools”. They do.

unified search layers   memory · knowledge · code · docs · sessions · plans
missing                 sources: 44,196 chunks · 29 topics · ~500 MB

The research corpus, every paper and saved article with its provenance tier, was not a layer. It had its own tool. Nothing pointed agents to it.

The A/B

Six queries on topics whose material lives only in the research corpus:

topicunified searchsources search
continuous thought machines0.6550.735
L-system plant architecture0.5190.655
reciprocal rank fusion0.6230.690
ontology platforms0.5940.627
neuro-symbolic reasoning0.6580.690
thermodynamics of AI flow0.6120.618

Sources won 6 of 6. “Continuous thought machines”, a topic with 226 files on disk, returned a constants file from another app and a CV draft at 0.55.

Second finding: we could not tell who uses retrieval

tool-usage counters    all 0. A ledger that records nothing.
retrieval log          3,501 entries: id · name · time · query hash
                       no tool, no actor, no collection

Michal’s question, is it available and used by the whole hive?, had no answer. What the log could show was worse:

memory files1,471
ever retrieved365 (24.8%)
never retrieved, not once1,106 (75%)
retrieved exactly once100
top 12 most retrieved8 are plans, handoffs or ledgers

The hive was mostly retrieving its own planning notes, not its knowledge.

What was not broken, measured so we stop suspecting it

  • Memory ingest: 1,469 of 1,470 files, 15,768 chunks, no incomplete chunk sets. The one skip is an empty file.
  • The chunker: paragraph-aware, 200-character overlap, keeps titles. One chunker, imported by both indexers.
  • The flat 0.0164 score: by design. Six disjoint corpora fused by rank give every first hit 1/(60+1). The field to read is relevance.

Three of our own mistakes in the same session

  • “172 unseen records” did not exist: we read the documentation in a hook instead of the code.
  • “The score is a degenerate bug” was the documented design: we read score instead of relevance.
  • “The docs corpus has 16 stacks”: the folder listing said 16, the tool said 24, and the tool was right.

What changed

Sources became a layer of the unified search (after the noise fixes, not before), and retrieval logging gained actor and tool fields. Without the second, the first could never be shown to matter.

Our records

The measurements in this article come from these records in the running system.

  • ~/memory/2026-10-28-MEASURED-hiveway-the-corpus-nobody-could-reach.md — 44,196 chunks behind a tool nobody routes to
Read next