noema/docs/site/pages/cognition.md

The cognitive cycle is the heart of a mind. It is deterministic code: given the same state, the same new events and the same recorded model responses, it produces the same thoughts in the same order. This page describes each stage, the processes that feed it, the modes that change it, and the metacognitive checks that watch it.

One cycle, end to end

1. Load state. The runtime holds the mind, its self-model, mode, cycle counter, workspace and working memory, active goals, drives, affect and the effective attention weights. State is persisted after every cycle and reloaded on start, so restarts are seamless.
2. Read new events. Events after the mind's cursor are read in sequence order. An event must have been recorded for at least a short settle window before it is seen, so backdated or in-flight events are not consumed half-written. A cycle triggered by a stimulus only proceeds if at least one of the new events came from outside the brain; a mind's own output never re-triggers it.
3. Observe. Every registered cognitive process looks at the state and the new events and returns thought candidates: a kind, a subject, a summary, a salience and confidence, evidence references and a feature vector. Processes run concurrently in a bounded pool with per-process timeouts and panic isolation; a slow or broken process cannot stall the cycle.
4. Score. Attention scoring computes ten features for each candidate, multiplies by the effective weights, and orders candidates by score with a stable tie-break on identifier. Every candidate is recorded as a thought_candidate event with its breakdown.
5. Admit. The top candidates enter the workspace up to capacity, displacing the weakest existing thoughts. Admissions are thought_selected events; the new workspace is a workspace_broadcast event; working memory decays and refreshes.
6. Dispatch. The executive runs the handler registered for each admitted thought's kind: encode a memory, create or update a belief, create a goal, register a prediction, generate a response, request an action. Handlers share the cycle's model-call cap.
7. Hooks and commit. After-cycle hooks update motivation, narrative and notifications. The whole cycle runs in one database transaction; events are published to live subscribers only after commit, so nobody ever sees a thought that was rolled back.
8. Advance. The cursor moves past the events that were read, a cycle_completed event records timing and counts, and the loop detector records the fingerprints of what was admitted.

The processes

Process	Produces	Deterministic?
Attend	candidates from new perception events, weighted by their salience, trust and urgency	yes
Retrieve	recalled memories relevant to what is in the workspace, with score breakdowns	yes (semantic component needs an embedding model)
Associate	low-confidence causal hypotheses when notable observations arrive close together	yes
Perceive	structured perception of messages and documents (entities, claims, questions, intent)	deterministic analysis, optionally enriched by a model
Goal monitor	progress, blockers and stalls on active goals	yes
Curiosity	questions about uncertain or contested beliefs, which can become investigation goals	yes
Metacognition	warnings about loops, contradictions, overconfidence and budget pressure	yes
Act	action requests when a thought calls for a capability	yes; execution goes through policy

Each process is a small Go type registered in code; there is no plugin loading and nothing a mind can do to add or change them.

Attention features

• salience from the event or memory that produced the candidate;
• urgency from time words, alert-like vocabulary and deadlines;
• novelty from how unlike recent workspace contents the candidate is;
• affect from the mind's current arousal and concern;
• goal_relevance from lexical overlap with active goals, weighted by priority;
• consequence from the candidate's kind (an action request weighs more than a recollection);
• confidence from the candidate's own confidence;
• contradiction when the candidate conflicts with a held belief;
• operator_priority when an operator injected or pinned it;
• context_relevance from overlap with the current conversation.

The weights are per mind (see configuration), modulated each cycle by drives and affect within bounds, and the effective values are stored on every selection event.

Modes

awake is the normal state. focused narrows admission to a conversation's context. idle lengthens the timer. reflecting, consolidating and dreaming are entered by the scheduler around the corresponding background job and left afterwards. paused stops cycles entirely until an operator resumes; events still accumulate and are processed on resume. All transitions are mode_changed events with a reason.

Metacognition

The metacognition process watches for the failure modes of a system that thinks in a loop: the same candidate fingerprint winning repeatedly (loop detector), a belief whose confidence moved far on little evidence, a contradiction left unresolved for too long, and model or cycle budgets running low. Each produces a metacognition event, a workspace warning and, when thresholds are crossed, a notification to the operator. Loops also suppress the repeating candidate for a while.

Operator controls

From the interface or noemactl workspace, an operator can trigger a cycle, pause and resume, reset the workspace or the motivation state, and reload configuration. Every control is an operator_action event in the mind's own history and an entry in the audit log, and the mind encodes it as an autobiographical memory: it knows it was changed.

{{include docs/cognition.md}}