Give the system a directory: ask who knows, then ask them

A memory system that only answers from its own store is a filing cabinet,
not a partner. The transactive rule the project is named for — not knowing
is fine when you know who does — needed a holder registry, a directory
query, and a referral that never leaks the text it may not read.

- schema v5 adds `holders` (person/agent/service, declared topics, contact).
  A holder with memories exists whether or not anybody registered them; the
  registry adds reachability, it does not grant existence.
- `who_knows` ranks holders by their own memories and is deliberately NOT
  filtered by visibility: "she knows" is the answer. The answer is filtered.
- `ask` searches the asker's visible scope first (hop 0), then walks the
  directory with a visited set and a hop budget. Three terminal states:
  answered, referred, no_holder_knows. Nobody knowing is a result, not an error.
- Confidence is ordinal, not calibrated: relative strength, coverage, and
  declared topics. Every hit carries the raw numbers and the basis lines that
  produced the score, so a ranking can be argued with.
- Faces: HTTP (/api/holders, /api/who_knows, /api/ask), CLI (holders,
  holder-set, holder-rm, who-knows, ask), MCP (who_knows, ask, list_holders).

Four bugs found by running the thing, not by reading it:
- FTS5 refuses bm25() inside MAX(); the aggregate uses FTS5's own `rank` column.
- A CJK question is longer than the sentence that answers it, so the whole-run
  phrase matched nothing. The query now ORs adjacent bigram phrases; adjacency
  is kept, equal length is not. Latin path untouched, baseline unaffected.
- The hop budget counted the asker as a hop, so max_hops=1 asked nobody.
- A second, stricter readability test in _answered() disagreed with the SQL
  visibility clause and hid a memory the asker was allowed to read. The SQL
  clause is the only authority now.

A method named `list` shadowed the builtin inside its own class and made
mypy reject the return annotation; renamed rather than cast around it.

Proof: 155 pytest, 12 Go tests, ruff and mypy clean on touched files, pyright
ledger unchanged at 62, and scripts/mcp_write_smoke.sh drives two principals
on one SQLite file — the husband asks through MCP, gets `referred` with his
wife's contact channel, and her private sentence appears nowhere in the reply.
This commit is contained in:
ZacharyZhang-NY committed 2026-10-07 17:20:45 -04:00
1 parent 9fe13fffb3
commit dfc6cd4c28
19 files changed
+1403 -19

No files matched your search

+16
View File
@@ -188,12 +188,18 @@ class Database:
until: datetime | None = None,
min_trust: float | None = None,
cartridge_ids: list[str] | None = None,
as_holder: str | None = None,
) -> FtsPage:
"""BM25 over the FTS index joined to memories that are open right now.
Every filter is a `? IS NULL OR` predicate in one literal statement: the ranking never
depends on string-built SQL, and the planner sees one shape. A memory with no event time
cannot answer a time filter, so it drops out when one is asked for.
`as_holder` applies the sharing rule: a memory is readable by its owner, by anyone named
in its visible_to list, by everyone when it is public, and by anyone when nobody owns it.
A memory with no holder cannot be private to a holder that does not exist. Without an
asker the query runs over the whole library, which is what an operator debugging wants.
"""
with self.connect() as connection:
rows = connection.execute(
@@ -221,6 +227,13 @@ class Database:
WHERE ca.atom_id = f.atom_id
AND ca.cartridge_id IN (SELECT value FROM json_each(?))
))
AND (? IS NULL OR a.holder_id = ''
OR json_extract(a.visibility_json, '$.scope') = 'everyone'
OR a.holder_id = ?
OR EXISTS (
SELECT 1 FROM json_each(json_extract(a.visibility_json, '$.holders'))
WHERE value = ?
))
ORDER BY score
LIMIT ? OFFSET ?
""",
@@ -242,6 +255,9 @@ class Database:
min_trust,
None if cartridge_ids is None else to_json(cartridge_ids),
None if cartridge_ids is None else to_json(cartridge_ids),
as_holder,
as_holder,
as_holder,
limit + 1,
offset,
),