Andy Dixon
8a018b1cce
docs/interpretation.md gains a table giving each word the interface and generated text use (believes, confidence, knows, remembers, attends, curious, wants, feels, expects, trusts, understands, reflects, dreams, self-model, metacognition, decides) its operational meaning: the stored state it names, the rule that changes it, where to inspect it and what it does not mean. docs/memory.md no longer describes a memory's confidence as "how likely the content is true"; it is the epistemic score defined in docs/beliefs.md.
3.5 KiB
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
confidencehow well supported the content is (the epistemic score defined in docs/beliefs.md, not a probability);importancehow much it matters;saliencehow strongly it presented itself.trustandcredibilitycome from the channel the information arrived through (operator > user ≈ system > tool > source > low). Credibility weighs retrieval and, later, belief confidence.activationis 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0.01 is still there, still linked, still readable.statusis active, retracted (an operator said it is inaccurate), superseded (replaced by a newer version) or archived.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_eventlinks to the event that produced the memory;memory_createdevents 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.