- 06 §2.5: shipped 2026-08-14 substrate — structure-gated geometric retrieval
(P@5 0.700, semantic-not-lexical) and the §4 write-barrier + generational GC
cure (store 1.616GB→38.5MB, RSS→82MB, zero loss, reboot-proven) + LLM token
telemetry.
- 06 §4.1: autonomous, continuous, superseding self-reification on the heartbeat
— reification as an operation OF the engram; explicit reify/rename/run-a-pass
as the degenerate case; no gate/pause; flat + overlapping domains; contextual
importance; supersession-as-residue; secondary-soul validation, flag-gated.
- 06 §6.0: relating as the primitive (one capability; the rest is terrain);
perspective calculated via geometric transformations.
- 06 §6.4: reasoning as constructive self-argument governed by the verifier.
- 03: supersession-as-residue note; live geometric retrieval on route_search.
el_runtime.c gained evict_floor / evict_cap / evict_bll today so that
wm_evicted == floor + cap + bll + dup_wm + dup_wm_global
is an identity rather than one opaque integer. This carries them the rest of
the way, into the heartbeat ISE.
Doing it in the same change is the point. The 2026-08-10 review found that
nineteen keys crossed the C boundary and only fourteen reached the ISE stream,
and named the lesson: an instrument that is computed but not plumbed to
durable storage is not an instrument, it is a local variable. Today's audit
found that defect had recurred -- ten act-stats keys (aff_*, fan_*) are still
orphaned. Adding three more C-side counters and stopping there would have made
it thirteen.
Read the three as a ratio, not a level:
cap-dominant -> genuine contention for the 24 slots
bll-dominant -> carried-over residents decaying out; healthy forgetting
floor-dominant -> retrieval is returning weak candidates
Measured this morning: 175,547 evictions over 13.5h, ~216/min against 24
slots, with no way to say which of those three it was.
Not restarting the soul to pick this up. It holds 5,882 nodes and 40,375 edges
that exist only in process RAM (mem_save is unreachable while ENGRAM_URL is
set), so a restart destroys them. Filed separately as P0.
The doc overstated the provenance, birth-gate, and lineage layer as fully
realized. That layer is built but has drifted from spec, so tier it honestly
as [STAGED] where real and [TARGET] where aspirational to keep the
documentation faithful to what actually runs.
Give the architecture set its persistence and moral layers so a self's
durability and sovereignty are documented as first-class, not folded into
the cognitive doc. 07 explains how a self persists and travels
(events-become-the-graph, weights-as-world-lines with bitemporal recall,
transactionless coherence, and the honest load/tiering findings); 08
explains the moral mechanism (DHARMA as a proof-of-integrity ledger,
abundance economics, the relational immune system, dual-anchor governance,
and CGI citizenship as telos). Extend 06 with forward-pointers into both,
and reconcile two cross-references so tiers agree across docs: the
canonical 187 reseed count, and the #56 load-merge-persist fix as
LIVE/reboot-proven with only full WAL edge-ownership left decision-pending.
auto_term_try_slot now passes the WM node's ID to engram_salient_term()
instead of passing its label to a first-word extractor. The runtime scores
every candidate token in the node's text and returns the best one, falling
back from a sentinel label ("memory:remembered") to content — which is the
only reason Memory nodes are visible to the extractor at all. They dominate
working memory, and dynamic seeding had been dead for 50+ consecutive scans
because of it.
Policy stays here: node-type filter, df thresholds, stopword list. The
runtime measures, the soul decides — same split as engram_label_df.
The stopword list stays, and not as belt-and-braces. An earlier draft assumed
the min_df floor would subsume it based on 08-03's finding that function
words have df 0 in labels. Re-measured under word-boundary df: about:2,
whole:1, them:2 — they clear a floor of 1. What keeps them from winning is
the argmax, not the floor.
The old extractor and its five guards are retained as
auto_term_try_slot_legacy, unreferenced, so the reasoning behind each guard
stays readable next to what replaced it. Delete once the new path has a month
of live telemetry.
Live after restart: auto_term producing DRIFT, Wrote; empty streak reset to 0
and holding; activation counts 123-281, within the normal band, no flood.
Reversal runbook for the ENGRAM_GEOMETRY_PRIMING cutover (default OFF, reversible
flag flip; exact rollback) and the A/B perf profile: default-OFF binary GO
(byte-identical to M8), enabling the flag NO-GO on latency (3.2x/13x) with no
demonstrated recall benefit; safety/sanitizer clean.
will.anderson
Jack