Andy Dixon
03631e5685
Phase 5 (ADR-0003). pkg/concepts fixes the epistemic vocabulary (observation, fact, memory, claim, hypothesis, belief, prediction, assumption, inference, opinion), memory kinds and relation names. internal/memory stores episodic, semantic, procedural and autobiographical memories in one mind-scoped table with trust-derived credibility, importance, salience and decaying activation. Retrieval fuses full-text rank (any-term by default), optional pgvector similarity, recency, activation, importance and credibility, and returns the component scores so every recall can be explained. Decay lowers activation and never deletes; retraction and supersession keep rows for provenance. Relationships are constrained to one mind at insert time. Embeddings live in a conditional pgvector table keyed by model so vector spaces are never mixed; without an embedder the system degrades to text and graph retrieval. Attention gates encoding: the attend handler turns admitted observations into episodic memories (operator changes become autobiographical ones) with memory_created events; the retrieve process proposes recalled memories as candidates and admitted recalls are reinforced with memory_retrieved events carrying their scoring components. Memory explorer UI (search with component breakdown, timeline, filters, operator knowledge entry), memory detail with provenance, relationships, citing events and an inaccurate-memory correction; API; noemactl memory commands; decay and embed-missing background jobs.
46 lines
3.4 KiB
Markdown
46 lines
3.4 KiB
Markdown
# Memory architecture
|
||
|
||
Noema keeps four long-term memory systems in one table (`memories`) distinguished by `kind`, plus an in-process working memory. Every record carries an explicit **epistemic kind** (observation, fact, memory, claim, hypothesis, belief, prediction, assumption, inference, opinion) so the system never confuses what it saw with what it inferred.
|
||
|
||
| Kind | What it holds | Created by |
|
||
|---|---|---|
|
||
| episodic | things that happened, with time, participants, channel, source | the `attend` handler when an observation wins attention; conversation |
|
||
| semantic | propositions and general knowledge | operators, belief formation, consolidation |
|
||
| procedural | how to do things (steps, preconditions, outcomes) | reflection, operators |
|
||
| autobiographical | the mind's own significant history | operator actions on the mind, reflection |
|
||
|
||
## Fields that matter
|
||
|
||
- `confidence` how likely the content is true; `importance` how much it matters; `salience` how strongly it presented itself.
|
||
- `trust` and `credibility` come from the channel the information arrived through (operator > user ≈ system > tool > source > low). Credibility weighs retrieval and, later, belief confidence.
|
||
- `activation` is accessibility. It rises on retrieval and decays over time (half-life 14 days, slowed by importance). **Decay never deletes**: a memory with activation 0.01 is still there, still linked, still readable.
|
||
- `status` is active, retracted (an operator said it is inaccurate), superseded (replaced by a newer version) or archived. Non-active memories stay for provenance and are excluded from normal recall.
|
||
- `origin_event` links to the event that produced the memory; `memory_created` events link back. Relationships (`related_to`, `supports`, `contradicts`, `derived_from`, …) carry confidence and source.
|
||
|
||
## Retrieval
|
||
|
||
`memory.Store.Retrieve` fuses independent signals, each recorded on the result:
|
||
|
||
| Component | Weight | Source |
|
||
|---|---|---|
|
||
| text | 0.40 (0.65 when vectors are unavailable) | PostgreSQL full-text rank; any-term matching by default, websearch syntax when strict |
|
||
| vector | 0.25 | pgvector cosine similarity for the configured embedding model |
|
||
| recency | 0.10 | exp(−age/30 days) |
|
||
| activation | 0.10 | current accessibility |
|
||
| importance | 0.10 | stored importance |
|
||
| credibility | 0.05 | source credibility |
|
||
|
||
The `retrieve` process runs this for every new observation and proposes recalled memories as thought candidates. Recall therefore competes for attention like everything else; admitted recalls are reinforced and produce `memory_retrieved` events containing the component scores.
|
||
|
||
## Embeddings
|
||
|
||
`memory_embeddings` exists only when pgvector is available. Rows carry the model name and dimensions, so switching embedding models never mixes vector spaces; a background job embeds memories that lack a vector for the current model. Without an embedder, retrieval is text plus graph plus recency and the system stays fully functional.
|
||
|
||
## Working memory
|
||
|
||
Working memory is the small, decaying set of items the mind is actively holding (default nine). It is part of the workspace snapshot, persists across restarts, and feeds the context-relevance feature of attention scoring. See `docs/adr/0001-global-workspace.md`.
|
||
|
||
## Operator corrections
|
||
|
||
"This memory is inaccurate" sets `status=retracted`, writes an `operator_action` event with the reason and an audit entry. The memory remains visible with a retracted badge; nothing is rewritten.
|