Give memories a working tier, a long-term tier, and a record of what disagrees

A memory used to have one state: present. A session could not be reloaded
without searching, nothing separated what a person said today from what the
store ingested a year ago, and two statements that disagree about a number
were both handed to the reader as if the store believed both.

Schema v10. Atoms gain session_id, importance, recall_count, last_recalled_at
and archived_at; two tables arrive beside them — consolidations (one watermark
per holder+scenario lane) and conflicts (a pair, the term they disagree on,
both values, and whether anyone has settled it). v_atoms_current now also
hides archived rows, and apply() drops the view before rebuilding it because
CREATE VIEW IF NOT EXISTS would keep the old body and ignore the archive.

Working memory is a read, not a store: `working <holder> <session>` returns
what that session recorded, in order, with no search involved. Consolidation
rolls a lane's new memories into one standing summary and moves the watermark
to the newest memory actually rolled up — not to the clock of the pass, which
made a second pass count the same memories twice. The archive rule is stated
in the command that runs it (recorded before N days, never returned by a
search, importance at or under a floor) rather than hidden in a decay formula
nobody measured; --dry-run names the victims first.

A conflict is recorded when a new memory repeats a label with a different
number in the same holder's same scenario. Retrieval drops the older side
while the conflict is open and both sides answer again once it is settled:
settling is not superseding, and a word-only disagreement is left alone
because a reworded sentence would fire on every paraphrase. Numbers are keyed
to both the memory's subject and the nearest preceding label, measured: the
two thermostat sentences share only their subject, so a nearest-word-only rule
found nothing.

Search now counts the memories it handed back, which is the only use estimate
the store has, and the archive rule reads it. The dense index applies the same
currency rules as the view, so an archived memory cannot stay findable through
one leg while the other hides it.

Two reads over HTTP (working, conflicts) and two tools over MCP
(working_set, memory_conflicts); curation stays with the operator because an
agent should not decide what its own past is worth. remember and supersede
carry a session id; importance does not cross MCP, because recall_count is
observed and importance is stated.

Gates: 366 passed; ruff clean; mypy 24 errors in 9 files, the recorded 9cb46c1
baseline, net 0; pyright 0 on the touched files; go build/vet/test and gofmt
clean; mcp_write_smoke PASS.

backend/src/ely_eye/retrieval.py

@@ -14,11 +14,11 @@ from datetime import datetime
 from pathlib import Path
 from typing import Any
 
-from . import cartridge_store
+from . import cartridge_store, lifecycle_store
 from .config import Settings, get_settings
 from .db import Database
 from .embeddings import EmbeddingService
-from .schemas import EvidenceAtom, RetrievalHit, SearchFilters, SearchResult
+from .schemas import EvidenceAtom, RetrievalHit, SearchFilters, SearchResult, utc_now
 from .store_search import FtsPage, search_atoms
 from .vector_index import VectorIndex
 from .visual_index import VisualIndex
@@ -89,7 +89,8 @@ class RetrievalService:
             rankings.append(list(visual))
             for atom_id, cosine in visual.items():
                 scores[atom_id]["visual_score"] = cosine
-        hits = self._rank(rankings, scores, limit)
+        hits = self._settle_conflicts(self._rank(rankings, scores, limit * CANDIDATE_WINDOW))[:limit]
+        lifecycle_store.touch_recalls(self.db, [hit.atom.atom_id for hit in hits], utc_now())
         more = page.has_more or len(rankings[0]) > limit
         return SearchResult(
             query=query,
@@ -179,6 +180,18 @@ class RetrievalService:
             )
         return hits
 
+    def _settle_conflicts(self, hits: list[RetrievalHit]) -> list[RetrievalHit]:
+        """Drop the older side of a disagreement nobody settled, so one page cannot contradict itself.
+
+        Both memories stay in the store and this only filters the page; the conflict row names
+        which side was dropped and why. Settling is the holder's call, and until it happens the
+        newer statement is what a reader should be shown.
+        """
+        losers = lifecycle_store.losing_sides(self.db, [hit.atom.atom_id for hit in hits])
+        if not losers:
+            return hits
+        return [hit for hit in hits if hit.atom.atom_id not in losers]
+
     def recall(self, query: str, top_k: int | None = None, *, filters: SearchFilters | None = None) -> list[EvidenceAtom]:
         """The atoms a search would put in front of a model, no scoring attached."""
         return [hit.atom for hit in self.search(query, top_k, filters=filters).hits]