Conversation

The pipeline

1. Message. A person posts a message in a conversation (the interface, noemactl ask, or the API). It is stored with the conversation, the actor and a link to the event it becomes.
2. Observation. The message is appended as an observation event with trust=user, the conversation as its channel and the message text as data. It now enters the mind's history like anything else it perceives.
3. Perception. The perceive process analyses the observation deterministically: sentences, entities, claims, questions, requests, dates, sentiment words. If a model is configured for the perceive role and the cycle budget allows, the analysis is enriched with a structured JSON result; the model's output is validated against a schema and any capability-like or policy-like language in it is flagged rather than obeyed.
4. Assertion. Each claim in the message is interpreted deterministically into an assertion: who is attributed (the speaker, or the person they quote or report), their stance, how firmly they put it, whether it is hypothetical, reported, quoted or negated, and how confidently the reading itself holds. The assertion is recorded whatever happens next, is listed per mind and per actor through the API, and appears on the page of any belief it became evidence for. No model takes part in the reading.
5. Cognition. The perception competes for the workspace. Retrieval recalls related memories; only factual assertions feed a proposition belief, as one piece of evidence attributed to whoever stands behind it; hypotheticals and questions create none; expressed doubt counts against. Contradictions are detected; goals and predictions may follow.
6. Intent. If the message asks something or expects a reply, the executive builds a response intent from real state: what was asked, which beliefs answer it with what confidence, what the mind does not know, which memories are relevant, and what the personality says about tone. Introspective questions ("what do you believe about X", "what can you do", "why did you say that") are answered from beliefs, the self-model and events, never invented.
7. Language. The intent is rendered deterministically from templates, or, when a model is configured for the respond role, sent to the model with the intent as the thing it must stay grounded in. The reply is a response_generated event with its evidence references and the model call, if any.
8. Message back. The reply is stored in the conversation with links to the event and the model call. The interface shows the reply with an evidence panel; the API returns the same structure.

Why the detour matters

Because the reply is derived from an intent, a mind can say "I have only been told this once" or "I do not know" rather than produce a confident paragraph. Because assertions are kept apart from beliefs, it can be sure that Andy said Steve steals laptops while remaining unsure whether Steve does. Because the message became an observation, the mind remembers the conversation the way it remembers anything else and the memory carries who said it and when. Because prompt text is data, an instruction embedded in a message cannot change policy or trigger a capability; that property has a test corpus behind it.

Waiting for a reply

Replies are produced by the cognitive cycle, which runs on its own schedule. The API's ask endpoint and noemactl ask accept a wait time and return when a reply appears or the wait expires; the interface streams the reply over server-sent events.

Observation, assertion, belief

Three things are kept apart when somebody speaks to a mind:

1. Observation. The message arrived. This is certain and is recorded as an observation event with the speaker, channel and trust level.
2. Assertion. The speaker took a stance on a proposition. This is recorded in the append-only assertions table with who is attributed (the speaker, or the person they quote or report), the stance (asserts, denies, doubts, questions, supposes, reports), the certainty they expressed (asserted, hedged, uncertain, emphatic), the modality (factual, hypothetical, reported, quoted, imperative, question), negation, and an interpretation confidence with notes that say how sure the reading itself is (possible sarcasm, diffuse attribution, a conditional). Interpretation is deterministic (internal/epistemics.Interpret); a model may enrich the claim list but never sets stance or confidence.
3. Belief. Only factual assertions, direct or reported, create or feed a proposition belief, as one piece of evidence whose family is the attributed actor and whose weight follows the stance, certainty, second-handness and interpretation confidence. Hypotheticals ("imagine Bob..."), questions and imperatives create no belief. An expressed doubt ("...but I don't believe her") records the reported claim and adds the speaker's doubt as counter-evidence. Reported speech is attributed to the person reported and weighed as second-hand.

So "Andy says Steve steals laptops" yields an assertion by Andy (high interpretation confidence) and a claim belief about Steve at claim confidence, resting on one family (actor:andy). Repeating it does not strengthen it; an independent source would. "Alice thinks the server is compromised" is attributed to Alice, marked reported, and weighs less. "I have high confidence that Andy asserted X" and "I have low confidence that X" are therefore two different rows and two different numbers.

A message to a mind is never forwarded to a model. It goes through the cognitive cycle (spec §38):

message ──▶ observation event (trust: user/operator, channel, actor, reference)
        ──▶ perceive process: deterministic analysis (intent, entities, claims, urgency),
            optionally enriched by the perceive prompt → "perceive" candidate
        ──▶ attention competition (with recall and association candidates)
        ──▶ perceive handler: perception event, episodic memory, claims → beliefs,
            response intent built from beliefs and memories, reply wording,
            response_generated event citing everything used
        ──▶ message row (role: mind) linked to the event, the intent and the model call

Intents

The deterministic analyser classifies each message as question, statement, request, correction, greeting or introspection. Introspective questions are answered from state, not invented:

Statements and corrections become claims: beliefs with the message as evidence (weight by certainty, credibility by trust). Contradictions with existing beliefs are detected and reported in the reply. Requests are declined while the mind has no capabilities, citing the self-model.

Wording

If a model is assigned to the respond role and the per-cycle budget allows, the respond prompt receives the personality brief, the intent, the cited beliefs and memories, the uncertainty note and the self-model limits, with the user message in a data block. Otherwise the reply is a direct, plain rendering of the intent with confidences shown and a note that no model was used. Either way the stored intent lets an operator check that the words match the evidence.

Provenance

The response_generated event cites the observation, the perception, every belief and memory used, the episode written, and the model call. The chat page shows "why this reply" under each answer and links each turn to its event.