The activation persist step was writing wm_weight=0 for every node not reached
by the current BFS fan-out. This destroyed working memory accumulated by
MCP-layer activations within one tick of the awareness loop firing on an empty
inbox. ACT-R and Soar treat spreading activation as additive: absent seeds
contribute zero spread, not a zero override of existing WM state.
Fix: non-reached nodes now decay by ENGRAM_WM_DECAY (0.7) per activation call
rather than being immediately zeroed. A hard floor of 0.005 clears near-zero
values to prevent infinite decay tails. Reached nodes behave unchanged.
Semantic seed floor raised 0.65 → 0.70: field literature (SuperLocalMemory
arXiv:2604.04514) validates 0.70-0.75 as the noise floor for sentence-transformer
embeddings on non-trivial corpora. The 0.65 threshold was admitting false
positives that diluted BFS traversal quality on the 13K-node post-ingestor graph.
Top-30 cap retained — sparse graph (1.26 edges/node) needs more semantic entry
points than a dense graph would.
ACT-R Base-Level Learning insight applied to engram_temporal_decay: current
purely time-based formula treated a node activated 100 times identically to a
node never activated (same decay rate). ACT-R BLL (Anderson 1993) shows
frequently-accessed memories resist temporal decay. Fix: freq_resist multiplier
= 1.0 + 0.1 * log(1 + activation_count). count=0→1.0×, count=9→1.23×,
count=99→1.46×. Existing activation_dampening continues to reduce per-query
novelty for well-known nodes — the two mechanisms are complementary: resist
decay (durable in graph), dampen per-query (don't dominate any single turn).
Three improvements from daily review:
1. Add semantic seed supplement to Pass 1 activation (el_runtime.c).
Previously, engram_cosine_sim was only called in goal_bias (Pass 2) for
nodes that already matched lexically. Nodes semantically close but
lexically disjoint were completely invisible to activation. With 8K+
world-ingestor nodes added overnight, this was a critical gap. Now: after
lexical seeding, scan un-seeded nodes for cosine sim ≥ 0.65 and inject
top-30 as additional seeds. Sem seeds get 85% of full act to stay weaker
than exact lexical matches.
2. Lower WM promotion ISE threshold from >0.5 to >0.1 (el_runtime.c).
Only one wm-promotion ISE was ever logged — the 0.5 floor was too high.
Most practical Knowledge/Memory promotions are in the 0.1-0.5 range.
Lowering to 0.1 makes working memory activity visible in state events.
Three research-grounded improvements:
1. Tier-based temporal decay in el_runtime.c (engram_node_full, engram_node_layered):
Working=48h, Episodic=72h, Semantic=336h, Procedural=720h half-lives.
Grounded in ACT-R literature — differentiated decay by chunk type. The
temporal_decay_rate field existed but was always 0 (global 168h for everything).
New nodes now carry the correct half-life for their tier from creation.
2. Implement route_neuron_knowledge_promote in server.el (was a silent stub):
Reads existing node, creates promoted-tier copy with supersedes edge,
checkpoints. promote_knowledge MCP tool now has real effect.
3. ISE label extraction + offset support in route_neuron_state_events:
POST now extracts 'event' field from content JSON as label (heartbeat,
wm_promotion, etc.) instead of always writing 'state-event'. GET now
accepts ?offset= for pagination to reach recent ISEs.
engram_cosine_sim was defined but never called. Nodes have 768-dim
nomic-embed-text vectors. Now:
- engram_embed_query() embeds the query string once per activate() call
- engram_goal_bias() takes (qvec, qdim) and adds cosine-similarity bonus
up to +0.6 when sim > 0.5 — semantic relevance now augments lexical bias
- engram_wm_count() exposes working-memory-active node count to EL
- el_runtime.h declares engram_wm_count for soul-daemon linking
- Add list_set, math_exp, and float_add/sub/mul/div/gt/lt/eq/gte/lte builtins to
el_runtime.c + el_runtime.h (float arithmetic builtins needed because EL operators
+*/ operate on raw el_val_t bits, not IEEE 754 doubles)
- Remove engram_embed_query() and its forward declaration from el_runtime.c
- Remove Ollama cosine-similarity blend from activation scoring (reverts 9af2482):
drops query_emb/query_edim variables, bias *= (1 + 0.3 * sim) block, and all
free(query_emb) calls from the activation loop
- Implement BM25+ scoring in server.el (k1=1.2, b=0.75, delta=1.0):
bm25_tokenize, bm25_count_term, bm25_score_doc, bm25_search_json
V1 uses n_t=1 approximation (constant IDF per corpus size); acceptable as a
first pass without an inverted index
- Wire /api/bm25/search POST/GET route in server.el dispatcher
- Zero Ollama calls in the activation/search path; embeddings on nodes are
untouched (still written at node-creation time)
engram_cosine_sim() was defined and embeddings were computed per-node
via nomic-embed-text on write, but the function was never called during
activation scoring. The goal_bias computation used only lexical substring
matching, ignoring all stored embedding vectors.
This change adds engram_embed_query() to embed the query string at search
time (5s timeout so Ollama latency never blocks activation), then blends
cosine similarity into the working-memory bias with α=0.3:
bias_final = goal_bias(lexical) * (1 + 0.3 * max(0, cosine_sim))
Nodes with high semantic similarity to the query but low lexical overlap
now receive up to 30% bias boost into working memory promotion. Gracefully
degrades to pure lexical when Ollama is unavailable or node has no embedding.
- Add ML-KEM-1024 + AES-256-GCM binary persistence to el_runtime.c with
two-key scheme (Neuron master + user key); SHAKE-256 key derivation
- Add nomic-embed-text 768-dim float32 embeddings on every node write
via Ollama; graceful fallback when Ollama is not running
- Wire all /api/neuron/* MCP routes directly into Engram (server.el),
eliminating the Kotlin server as the MCP backend
- Set ENGRAM_CHECKPOINT_INTERVAL = 1 (write binary on every node write,
not every 50)
- Add el_runtime.h declarations for engram_write_binary_el and
engram_load_binary_el builtins
will.anderson
Will Anderson