memory: a fact written under a new spelling of its key merges into the one that survives ...

The extractor invents a key every time it meets the same fact — `language`,
`preferred_language`, `ui_language` — and the upsert keys on the exact string, so
the base grew several spellings of each durable fact. On prod, 24 facts across 11
clusters share a key once noise prefixes are dropped, 10 of them under the exact
same value.

upsert_fact(dedupe=True) now compares the *tokens* of the normalized key — set
equality, not overlap, and never the value: `ui_language` and `language` are one
key while `dark` and `dark_ui` are two. The row already holding the writer's exact
key wins; otherwise the incoming one does. Losers are marked, not deleted: each
keeps its key and its value and gains `merged_into`, so the merge is reversible
with one UPDATE. Off by default, so the memory tool still writes exactly the row
it asked for.

Every read path filters `merged_into IS NULL`, and the mark is reachable only
where it is meant to be — get_all_facts/fact_count gained include_merged, and
GET /admin/memory?include_merged=true exposes it. search_facts deliberately has
no such flag: the injection path must not be able to see a hidden row. Forgetting
a key drops its hidden aliases first, so none is left pointing at nothing.

Three fixes that fell out of the same read:

- expires_at was overwritten with EXCLUDED.expires_at on every upsert, and the
  extractor always passes None — so it silently cleared any expiry the agent had
  set. Both DO UPDATE clauses now COALESCE.
- The ILIKE fallback was the one read path that served expired facts.
- The `list` action promised "all stored facts" and returned categories. The code
  was right and the description was wrong; the description now says so.

The extraction prompt stopped allowing infrastructure — servers, hosts, addresses,
running services — while the agent and the planner already forbade it; that
loophole is where 423 technical facts came from. It also forbids secrets outright,
and asks for stable snake_case keys. Expiry is now documented as being for facts
with a known end, not for facts you merely doubt.

Facts reach the prompt with their age ("updated 34d ago") alongside confidence:
nothing expires on a clock, so the injection says how old a fact is and lets the
agent weigh it.

memory+llm: three failures the prod logs gave up ...

All three came out of a survey of the last days of journalctl on prod,
and each one silently destroyed something the user had already paid for.

memory_facts: the no-embedding INSERT bound $13 while its column list
had 12 entries, so every fact written while the embedding backend was
down died on PostgresSyntaxError and the extraction was lost — 47
embed failures in three days, most of them landing in this branch.

Embedding input now gets clipped instead of 400'd away. A 400 takes the
whole embedding with it and recall drops to ILIKE over everything; a
reaction-session prompt (a full event envelope inlined) did that 41
times. settings.embedding_max_chars (6000, 0 disables) caps the input
at the model's window, so recall still works on the head of the text.

Message strips NUL bytes at the model boundary. PostgreSQL text cannot
hold one, and a NUL arriving in a tool result (reading a binary file)
made the whole session_messages INSERT fail with
CharacterNotInRepertoireError — the turn died and the user lost it.
Three times on 2026-10-07. As a Message validator it covers every
writer downstream: session store, kv store, memory extraction.

Each new test was checked to fail with its fix reverted.

Fix admin memory showing 0 facts; add pagination/search/sort ...

Bug fix:
- get_all_facts(user_id=None) was filtering for user_id IS NULL only,
  so admin panel showed 0 facts when facts had user_ids set.
- Added all_users parameter to get_all_facts and fact_count.
- Admin endpoint now passes all_users=True to return all facts.

Memory pagination:
- Extended get_all_facts with offset, search, sort_by, sort_order params.
- Extended fact_count with search and all_users params.
- /admin/memory endpoint now accepts limit, offset, search, sort_by,
  sort_order and returns {total, limit, offset, items}.

Admin panel frontend:
- Added server-side search with debounce for memory facts.
- Added sortable column headers (category, key, source, confidence, updated).
- Added pagination controls (prev/next, page size selector).
- Switched memory display from grouped tables to flat sortable table.

Tests:
- Added unit tests for get_all_facts(all_users=True) and
  fact_count(all_users=True).
- All 219 tests pass.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Phase 2 — Memory store + extractor unit tests ...

- tests/conftest_factory.py: add FakeRecord, FakeConnection, FakePool, make_store_with_pool
- tests/unit/memory/test_store.py: 18 tests for upsert, vector/ILIKE search, delete, list, count, summary, session state, backfill
- tests/unit/memory/test_extractor.py: 11 tests for JSON extraction, invalid JSON, empty response, tool result truncation, summary regeneration
- docs/testing.md: update coverage status, add FakePool usage example

88 total tests passing (59 + 29).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>