You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 1d5a534
Browse filesBrowse the repository at this point in the historyBrowse files
#562. The docs, the recall tool description and the MCP prompt called the
read path "6-signal WRRF" (vector, BM25, heat, Hopfield, HDC, SR). The
code fuses five signals inside the database: vector, full-text
(ts_rank_cd / FTS5), trigram, effective heat and recency. PostgreSQL
combines them as a weighted sum of max-normalised scores
(infrastructure/pg_schema.py, recall_memories()); SQLite uses rank-based
WRRF without the trigram signal (infrastructure/sqlite_store_search.py).
Hopfield and HDC run after fusion (core/pg_recall_stages.py). Corrected in
docs/mcp-tools.md, docs/architecture.md, docs/api-reference.md,
docs/data-flow.md (diagram and signal tables), README.md, the recall
handler's description strings and mcp_prompts.py. ADR-013 keeps its
original design text with a dated note, written in the canonical wiki page
and mirrored by scripts/check_project_wiki.py --write.
#563. docs/module-inventory.md stored four per-layer file counts that had
drifted from the tree. A count in this page changes with every new module
and no gate can hold it exactly without conflicting across parallel
branches, so the page now gives the measurement command instead.
Co-authored-by: Claude Opus 5 (1M context) <[email protected]>
-*Note, 2026-09-15 (#562):* this is the original design. The shipped read path fuses five signals inside the database (vector, full-text, trigram, heat, recency): a weighted sum of max-normalised scores on PostgreSQL (`recall_memories()` in `mcp_server/infrastructure/pg_schema.py`), rank-based WRRF on SQLite without the trigram signal (`mcp_server/infrastructure/sqlite_store_search.py`). Hopfield and HDC run after fusion (`mcp_server/core/pg_recall_stages.py`); Successor Representation is not on the `recall` path.
35
36
-**HDC encoder** (`hdc_encoder.py`): 1024-dimensional bipolar hypervectors for content-addressable similarity
36
37
-**Cognitive map** (`cognitive_map.py`): Successor Representation transition matrix from co-access patterns + 2D eigendecomposition projection
37
38
-**Fractal hierarchy** (`fractal.py`): L0/L1/L2 hierarchical clustering for multi-scale recall
Retrieve memories by fusing five signals server-side (vector, full-text, trigram, heat, recency; the SQLite backend has no trigram signal), then Hopfield, HDC and spreading-activation reranks, then FlashRank.
3.**Fuse**: PL/pgSQL `recall_memories()` fuses vector, FTS (`ts_rank_cd`), trigram, heat and recency server-side as a weighted sum of max-normalised scores. The SQLite backend fuses vector, FTS5, heat and recency by rank, w/(k + rank), with no trigram signal
143
+
4.**Recollect**: Hopfield completion, HDC, optional spreading activation, dendritic, emotional and mood reranks, reconsolidation, each blended by RRF k = 60
-*Note, 2026-09-15 (#562):* this is the original design. The shipped read path fuses five signals inside the database (vector, full-text, trigram, heat, recency): a weighted sum of max-normalised scores on PostgreSQL (`recall_memories()` in `mcp_server/infrastructure/pg_schema.py`), rank-based WRRF on SQLite without the trigram signal (`mcp_server/infrastructure/sqlite_store_search.py`). Hopfield and HDC run after fusion (`mcp_server/core/pg_recall_stages.py`); Successor Representation is not on the `recall` path.
33
34
-**HDC encoder** (`hdc_encoder.py`): 1024-dimensional bipolar hypervectors for content-addressable similarity
34
35
-**Cognitive map** (`cognitive_map.py`): Successor Representation transition matrix from co-access patterns + 2D eigendecomposition projection
35
36
-**Fractal hierarchy** (`fractal.py`): L0/L1/L2 hierarchical clustering for multi-scale recall
0 commit comments